Numerous lines of work aim to control \emph{model disagreement} — the extent to which two machine learning models disagree in their predictions. We adopt a simple and standard notion of model disagreement in real-valued prediction problems, namely the expected squared difference in predictions between two models trained on independent samples, without any coordination of the training processes. We would like to be able to drive disagreement to zero with some natural parameter(s) of the training procedure using analyses that can be applied to existing training methodologies. We develop a simple general technique for proving bounds on independent model disagreement based on \emph{anchoring} to the average of two models within the analysis. We then apply this technique to prove disagreement bounds for four commonly used machine learning algorithms: (1) stacked aggregation over an arbitrary model class (where disagreement is driven to 0 with the number of models $k$ being stacked) (2) gradient boosting (where disagreement is driven to 0 with the number of iterations $k$) (3) neural network training with architecture search (where disagreement is driven to 0 with the size $n$ of the architecture being optimized over) and (4) regression tree training over all regression trees of fixed depth (where disagreement is driven to 0 with the depth $d$ of the tree architecture). For clarity, we work out our initial bounds in the setting of one-dimensional regression with squared error loss — but then show that all of our results generalize to multi-dimensional regression with any strongly convex loss.

OBJECTIVE: To support ambulatory care innovation, we created Observer, a multimodal dataset comprising videotaped outpatient visits, electronic health record (EHR) data, and structured surveys. This paper describes the data collection procedures and summarizes the clinical and contextual features of the dataset. MATERIALS AND METHODS: A multistakeholder steering group shaped recruitment strategies, survey design, and privacy-preserving design. Consented patients and primary care providers (PCPs) were recorded using room-view and egocentric cameras. EHR data, metadata, and audit logs were also captured. A custom de-identification pipeline, combining transcript redaction, voice masking, and facial blurring, ensured video and EHR HIPAA compliance. RESULTS: We report on the first 100 visits in this continually growing dataset. Thirteen PCPs from 4 clinics participated. Recording the first 100 visits required approaching 210 patients, from which 129 consented (61%), with 29 patients missing their scheduled encounter after consenting. Visit lengths ranged from 5 to 100 minutes, covering preventive care to chronic disease management. Survey responses revealed high satisfaction: 4.24/5 (patients) and 3.94/5 (PCPs). Visit experience was unaffected by the presence of video recording technology. DISCUSSION: We demonstrate the feasibility of capturing rich, real-world primary care interactions using scalable, privacy-sensitive methods. Room layout and camera placement were key influences on recorded communication and are now added to the dataset. The Observer dataset enables future clinical AI research/development, communication studies, and informatics education among public and private user groups. CONCLUSION: Observer is a new, shareable, real-world clinic encounter research and teaching resource with a representative sample of adult primary care data.

• Introduce a novel object-centric self-supervised representation learning model based on bidirectional temporal reasoning across video frames. • Introduce slot-contrastive loss, specifically designed for slot attention, to improve orthogonality between slots. • Superior temporal coherence and zero-shot generalization across four surgical video datasets from three different domains: abdominal, cholecystectomy, and thoracic surgery. Object-centric slot attention is a powerful framework for unsupervised learning of structured and explainable representations that can support reasoning about objects and actions, including in surgical video. However, current object-centric models either fail to reliably capture object dependencies in seconds-long video episodes that encompass surgical actions and tasks or are computationally too expensive for practical implementation. We introduce Slot-BERT, a slot attention model with a temporal slot transformer module to overcome these limitations. Our core innovations are: 1) A bidirectional transformer module that processes object-centric slot representations, enabling longer-range temporal coherence; 2) A slot-contrastive loss that further improves the representation by enforcing slot dissimilarity; 3) We evaluate Slot-BERT on real-world surgical video datasets from abdominal, cholecystectomy, and thoracic procedures, and on real and synthetic videos with everyday objects. Our method surpasses state-of-the-art object-centric approaches under unsupervised training achieving superior performance across these domains. We also demonstrate efficient zero-shot domain adaptation to data from diverse surgical specialties and databases.

Multimodal large language models (MLLMs) can simultaneously process visual, textual, and auditory data, capturing insights that complement human analysis. However, existing video question-answering (VidQA) benchmarks and datasets often exhibit a bias toward a single modality, despite the goal of requiring advanced reasoning skills that integrate diverse modalities to answer the queries. In this work, we introduce the modality importance score (MIS) to identify such bias. It is designed to assess which modality embeds the necessary information to answer the question. Additionally, we propose an innovative method using state-of-the-art MLLMs to estimate the modality importance, which can serve as a proxy for human judgments of modality perception. With this MIS, we demonstrate the presence of unimodal bias and the scarcity of genuinely multimodal questions in existing datasets. We further validate the modality importance score with multiple ablation studies to evaluate the performance of MLLMs on permuted feature sets. Our results indicate that current models do not effectively integrate information due to modality imbalance in existing datasets. Our proposed MLLM-derived MIS can guide the curation of modality-balanced datasets that advance multimodal learning and enhance MLLMs' capabilities to understand and utilize synergistic relations across modalities.

Interactive 3D simulated objects are crucial in AR/VR, animations, and robotics, driving immersive experiences and advanced automation. However, creating these articulated objects requires extensive human effort and expertise, limiting their broader applications. To overcome this challenge, we present Articulate-Anything, a system that automates the articulation of diverse, complex objects from many input modalities, including text, images, and videos. Articulate-Anything leverages vision-language models (VLMs) to generate code that can be compiled into an interactable digital twin for use in standard 3D simulators. Our system exploits existing 3D asset datasets via a mesh retrieval mechanism, along with an actor-critic system that iteratively proposes, evaluates, and refines solutions for articulating the objects, self-correcting errors to achieve a robust out- come. Qualitative evaluations demonstrate Articulate-Anything's capability to articulate complex and even ambiguous object affordances by leveraging rich grounded inputs. In extensive quantitative experiments on the standard PartNet-Mobility dataset, Articulate-Anything substantially outperforms prior work, increasing the success rate from 8.7-11.6\% to 75\% and setting a new bar for state-of-art performance. We further showcase the utility of our generated assets by using them to train robotic policies for fine-grained manipulation tasks that go beyond basic pick and place.

We reframe scene flow as the task of estimating a continuous space-time ordinary differential equation (ODE) that describes motion for an entire observation sequence, represented with a neural prior. Our method, EulerFlow, optimizes this neural prior estimate against several multi-observation reconstruction objectives, enabling high quality scene flow estimation via self-supervision on real-world data. EulerFlow works out-of-the-box without tuning across multiple domains, including large-scale autonomous driving scenes and dynamic tabletop settings. Remarkably, EulerFlow produces high quality flow estimates on small, fast moving objects like birds and tennis balls, and exhibits emergent 3D point tracking behavior by solving its estimated ODE over long-time horizons. On the Argoverse 2 2024 Scene Flow Challenge, EulerFlow outperforms all prior art, surpassing the next-best unsupervised method by more than 2.5 times, and even exceeding the next-best supervised method by over 10%. See https://vedder.io/eulerflow for interactive visuals.

Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient steps for every new sample. While such high update-to-data (UTD) ratios have shown strong empirical performance, they also introduce instability to the training process. Previous approaches need to rely on periodic neural network parameter resets to address this instability, but restarting the training process is infeasible in many real-world applications and requires tuning the resetting interval. In this paper, we focus on one of the core difficulties of stable training with limited samples: the inability of learned value functions to generalize to unobserved on-policy actions. We mitigate this issue directly by augmenting the off-policy RL training process with a small amount of data generated from a learned world model. Our method, Model-Augmented Data for TD Learning (MAD-TD) uses small amounts of generated data to stabilize high UTD training and achieve competitive performance on the most challenging tasks in the DeepMind control suite. Our experiments further highlight the importance of employing a good model to generate data, MAD-TD's ability to combat value overestimation, and its practical stability gains for continued learning.

In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it is important to optimize over multiple objectives simultaneously. For example, when we are interested in fairness, states might have feature annotations corresponding to multiple (intersecting) demographic groups to whom reward accrues, and our goal might be to maximize the reward of the group receiving the minimal reward. In this work, we consider a multi-objective optimization problem in which each objective is defined by a state-based reweighting of a single scalar reward function. This generalizes the problem of maximizing the reward of the minimum reward group. We provide oracle-efficient algorithms to solve these multi-objective RL problems even when the number of objectives is very large — for tabular MDPs, as well as for large MDPs when the group functions have additional structure. The contribution of this paper is that we are able to solve this class of multi-objective RL problems with a possibly exponentially large class of constraints over intersecting groups in both tabular and large state space MDPs in an oracle-efficient manner. Finally, we experimentally validate our theoretical results and demonstrate applications on a preferential attachment graph MDP.

Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require features that are jointly informative across clients while disentangling domain-specific factors without supervision. We introduce FORLA, a novel framework for federated object-centric representation learning and feature adaptation across clients using unsupervised slot attention. At the core of our method is a shared feature adapter, trained collaboratively across clients to adapt features from foundation models, and a shared slot attention module that learns to reconstruct the adapted features. To optimize this adapter, we design a two-branch student–teacher architecture. In each client, a student decoder learns to reconstruct full features from foundation models, while a teacher decoder reconstructs their adapted, low-dimensional counterpart. The shared slot attention module bridges cross-domain learning by aligning object-level representations across clients. Experiments in multiple real-world datasets show that our framework not only outperforms centralized baselines on object discovery but also learns a compact, universal representation that generalizes well across domains. This work highlights federated slot attention as an effective tool for scalable, unsupervised visual representation learning from cross-domain data with distributed concepts.

Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring extensive annotations of object masks, relying instead on coarse video labels indicating object presence. WSVOS in surgical videos is, however, more challenging due to the complex interaction of multiple transient objects, such as surgical tools moving in and out of the surgical field. In this scenario, state-of-the-art WSVOS methods struggle to learn accurate segmentation maps. We address this problem by introducing ViDeo Spatio-Temporal disentanglement Networks (VDST-Net), a framework to disentangle complex spatio-temporal object interactions using semi-decoupled knowledge distillation to predict high-quality class activation maps (CAMs). A teacher network is designed to help a temporal-reasoning student network resolve activation conflicts, as the student leverages temporal dependencies when specifics about object location and timing in the video are not provided. We demonstrate the efficacy of our framework on a challenging surgical video dataset where objects are, on average, present in less than 60% of annotated frames, and compare our method to state-of-the-art methods on surgical data and on a public dataset commonly used to benchmark WSVOS. Our method outperforms state-of-the-art techniques and generates accurate segmentation masks under video-level weak supervision. Our code is available at: https://github.com/PCASOlab/VDST-net.

OBJECTIVE: The increasing use of audio-video (AV) data in healthcare has improved patient care, clinical training, and medical and ethnographic research. However, it has also introduced major challenges in preserving patient-provider privacy due to Protected Health Information (PHI) in such data. Traditional de-identification methods are inadequate for AV data, which can reveal identifiable information such as faces, voices, and environmental details. Our goal was to create a pipeline for de-identifying AV healthcare data that minimized the human effort required to guarantee successful de-identification. METHODS: We combined open-source tools with novel methods and infrastructure into a six-stage pipeline: (1) transcript extraction using WhisperX, (2) transcript de-identification with an adapted PHIlter, (3) audio de-identification through scrubbing, (4) video de-identification using YOLOv11 for pose detection and blurring, (5) recombining de-identified audio and video, and (6) validation and correction via manual quality control (QC). We developed two de-identification strategies to support different tolerances for lossy video images. We evaluated this pipeline using 10 h of simulated clinical AV recordings, comprising nearly 1.1 million video frames and approximately 72,000 words. RESULTS: In Precision Privacy Preservation (PPP) mode, MedVidDeId achieved a success rate of 50%, while in Greedy Privacy Preservation (GPP) mode, it achieved a 97.5% success rate. Compared to manual methods for a 15 min video segment, the pipeline reduced de-identification time by 26.7% in PPP and 64.2% in GPP modes. CONCLUSION: The MedVidDeID pipeline offers a viable, efficient hybrid solution for handling AV healthcare data and privacy preservation. Future work will focus on reducing upstream errors at each stage and minimizing the role of the human in the loop.

Roughly every decade, the ACM and IEEE professional organizations have produced recommendations for the education of undergraduate computer science students. These guidelines are used worldwide by research universities, liberal arts colleges, and community colleges. For the latest 2023 revision of the curriculum, AAAI has collaborated with ACM and IEEE to integrate artificial intelligence more broadly into this new curriculum and to address the issues it raises for students, instructors, practitioners, policy makers, and the general public. This paper describes the development process and rationale that underlie the artificial intelligence components of the CS2023 curriculum, discusses the challenges in curriculum design for such a rapidly advancing field, and examines lessons learned during this three-year process.

Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to process full-size point clouds, making them unusable as computer vision primitives for real-time applications such as open world object detection. Feedforward methods are considerably faster, running on the order of tens to hundreds of milliseconds for full-size point clouds, but require expensive human supervision. To address both limitations, we propose _Scene Flow via Distillation_, a simple, scalable distillation framework that uses a label-free optimization method to produce pseudo-labels to supervise a feedforward model. Our instantiation of this framework, _ZeroFlow_, achieves **state-of-the-art** performance on the _Argoverse 2 Self-Supervised Scene Flow Challenge_ while using zero human labels by simply training on large-scale, diverse unlabeled data. At test-time, ZeroFlow is over 1000$\times$ faster than label-free state-of-the-art optimization-based methods on full-size point clouds (34 FPS vs 0.028 FPS) and over 1000$\times$ cheaper to train on unlabeled data compared to the cost of human annotation (\\$394 vs ~\\$750,000). To facilitate further research, we will release our code, trained model weights, and high quality pseudo-labels for the Argoverse 2 and Waymo Open datasets.

Despite outstanding semantic scene segmentation in closed-worlds, deep neural networks segment novel instances poorly, which is required for autonomous agents acting in an open world. To improve out-of-distribution (OOD) detection for segmentation, we introduce a metacognitive approach in the form of a lightweight module that leverages entropy measures, segmentation predictions, and spatial context to characterize the segmentation model’s uncertainty and detect pixel-wise OOD data in real-time. Additionally, our approach incorporates a novel method of generating synthetic OOD data in context with in-distribution data, which we use to fine-tune existing segmentation models with maximum entropy training. This further improves the metacognitive module’s performance without requiring access to OOD data while enabling compatibility with established pre-trained models. Our resulting approach can reliably detect OOD instances in a scene, as shown by state-of-the-art performance on OOD detection for semantic segmentation benchmarks.

Road traffic scene reconstruction from videos has been desirable by road safety regulators, city planners, researchers, and autonomous driving technology developers. However, it is expensive and unnecessary to cover every mile of the road with cameras mounted on the road infrastructure. This paper presents a method that can process aerial videos to vehicle trajectory data so that a traffic scene can be automatically reconstructed and accurately re-simulated using computers. On average, the vehicle localization error is about 0.1 m to 0.3 m using a consumer-grade drone flying at 120 meters. This project also compiles a dataset of 50 reconstructed road traffic scenes from about 100 hours of aerial videos to enable various downstream traffic analysis applications and facilitate further road traffic related research. The dataset is available at https://github.com/duolu/CAROM.

The replicability crisis in the social, behavioral, and data sciences has led to the formulation of algorithm frameworks for replicability --- i.e., a requirement that an algorithm produce identical outputs (with high probability) when run on two different samples from the same underlying distribution. While still in its infancy, provably replicable algorithms have been developed for many fundamental tasks in machine learning and statistics, including statistical query learning, the heavy hitters problem, and distribution testing. In this work we initiate the study of replicable reinforcement learning, providing a provably replicable algorithm for parallel value iteration, and a provably replicable version of R-Max in the episodic setting. These are the first formal replicability results for control problems, which present different challenges for replication than batch learning settings.

Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order to successfully transfer information from one task to another, it is critical to understand the similarities and differences between the domains. In this paper, we introduce the notion of performance gap, an intuitive and novel measure of the distance between learning tasks. Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e.g., $\mathcal{H}$-divergence or discrepancy distance), we theoretically show that the performance gap can be viewed as a data- and algorithm-dependent regularizer, which controls the model complexity and leads to finer guarantees. More importantly, it also provides new insights and motivates a novel principle for designing strategies for knowledge sharing and transfer: gap minimization. We instantiate this principle with two algorithms: 1. gapBoost, a novel and principled boosting algorithm that explicitly minimizes the performance gap between source and target domains for transfer learning; and 2. gapMTNN, a representation learning algorithm that reformulates gap minimization as semantic conditional matching for multitask learning. Our extensive evaluation on both transfer learning and multitask learning benchmark data sets shows that our methods outperform existing baselines.

Bird's Eye View (BEV) is a popular representation for processing 3D point clouds, and by its nature is fundamentally sparse. Motivated by the computational limitations of mobile robot platforms, we create a fast, high-performance BEV 3D object detector that maintains and exploits this input sparsity to decrease runtimes over non-sparse baselines and avoids the tradeoff between pseudoimage area and runtime. We present results on KITTI, a canonical 3D detection dataset, and Matterport-Chair, a novel Matterport3D-derived chair detection dataset from scenes in real furnished homes. We evaluate runtime characteristics using a desktop GPU, an embedded ML accelerator, and a robot CPU, demonstrating that our method results in significant detection speedups (2 × or more) for embedded systems with only a modest decrease in detection quality. Our work represents a new approach for practitioners to optimize models for embedded systems by maintaining and exploiting input sparsity throughout their entire pipeline to reduce runtime and resource usage while preserving detection performance. All models, weights, experimental configurations, and datasets used are publicly available11https://vedder.io/sparse_point_pillars.

Effective lifelong learning across diverse tasks requires the transfer of diverse knowledge, yet transferring irrelevant knowledge may lead to interference and catastrophic forgetting. In deep networks, transferring the appropriate granularity of knowledge is as important as the transfer mechanism, and must be driven by the relationships among tasks. We first show that the lifelong learning performance of several current deep learning architectures can be significantly improved by transfer at the appropriate layers. We then develop an expectation-maximization (EM) method to automatically select the appropriate transfer configuration and optimize the task network weights. This EM-based selective transfer is highly effective, balancing transfer performance on all tasks with avoiding catastrophic forgetting, as demonstrated on three algorithms in several lifelong object classification scenarios.

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong learning setting, in which an agent is faced with multiple consecutive tasks over its lifetime, reusing information from previously seen tasks can substantially accelerate the learning of new tasks. We provide a novel method for lifelong policy gradient learning that trains lifelong function approximators directly via policy gradients, allowing the agent to benefit from accumulated knowledge throughout the entire training process. We show empirically that our algorithm learns faster and converges to better policies than single-task and lifelong learning baselines, and completely avoids catastrophic forgetting on a variety of challenging domains.

Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task.

After years of taking a trial-and-error approach to managing a moderate-size academic research group, I settled on using a set of online tools and protocols that seem effective, require relatively little effort to use and maintain, and are inexpensive. This paper discusses this approach to communication, project management, document and code management, and logistics. It is my hope that other researchers, especially new faculty and research scientists, might find this set of tools and protocols useful when determining how to manage their own research group. This paper is targeted toward research groups based in mathematics and engineering, although faculty in other disciplines may find inspiration in some of these ideas.

Current mechanisms for knowledge transfer in deep networks tend to either share the lower layers between tasks, or build upon representations trained on other tasks. However, existing work in non-deep multi-task and lifelong learning has shown success with using factorized representations of the model parameter space for transfer, permitting more flexible construction of task models. Inspired by this idea, we introduce a novel architecture for sharing latent factorized representations in convolutional neural networks (CNNs). The proposed approach, called a deconvolutional factorized CNN, uses a combination of deconvolutional factorization and tensor contraction to perform flexible transfer between tasks. Experiments on two computer vision data sets show that the DF-CNN achieves superior performance in challenging lifelong learning settings, resists catastrophic forgetting, and exhibits reverse transfer to improve previously learned tasks from subsequent experience without retraining.

We propose a new principle for transfer learning, based on a straightforward intuition: if two domains are similar to each other, the model trained on one domain should also perform well on the other domain, and vice versa. To formalize this intuition, we define the performance gap as a measure of the discrepancy between the source and target domains. We derive generalization bounds for the instance weighting approach to transfer learning, showing that the performance gap can be viewed as an algorithm-dependent regularizer, which controls the model complexity. Our theoretical analysis provides new insight into transfer learning and motivates a set of general, principled rules for designing new instance weighting schemes for transfer learning. These rules lead to gapBoost, a novel and principled boosting approach for transfer learning. Our experimental evaluation on benchmark data sets shows that gapBoost significantly outperforms previous boosting-based transfer learning algorithms.

Methods for learning from demonstration (LfD) have shown success in acquiring behavior policies by imitating a user. However, even for a single task, LfD may require numerous demonstrations. For versatile agents that must learn many tasks via demonstration, this process would substantially burden the user if each task were learned in isolation. To address this challenge, we introduce the novel problem of lifelong learning from demonstration, which allows the agent to continually build upon knowledge learned from previously demonstrated tasks to accelerate the learning of new tasks, reducing the amount of demonstrations required. As one solution to this problem, we propose the first lifelong learning approach to inverse reinforcement learning, which learns consecutive tasks via demonstration, continually transferring knowledge between tasks to improve performance.

No two robots are exactly the same-even for a given model of robot, different units will require slightly different controllers. Furthermore, because robots change and degrade over time, a controller will need to change over time to remain optimal. This paper leverages lifelong learning in order to learn controllers for different robots. In particular, we show that by learning a set of control policies over robots with different (unknown) motion models, we can quickly adapt to changes in the robot, or learn a controller for a new robot with a unique set of disturbances. Furthermore, the approach is completely model-free, allowing us to apply this method to robots that have not, or cannot, be fully modeled.

The success of applying policy gradient reinforcement learning (RL) to difficult control tasks hinges crucially on the ability to determine a sensible initialization for the policy. Transfer learning methods tackle this problem by reusing knowledge gleaned from solving other related tasks. In the case of multiple task domains, these algorithms require an inter-task mapping to facilitate knowledge transfer across domains. However, there are currently no general methods to learn an inter-task mapping without requiring either background knowledge that is not typically present in RL settings, or an expensive analysis of an exponential number of inter-task mappings in the size of the state and action spaces. This paper introduces an autonomous framework that uses unsupervised manifold alignment to learn inter-task mappings and effectively transfer samples between different task domains. Empirical results on diverse dynamical systems, including an application to quadrotor control, demonstrate its effectiveness for cross-domain transfer in the context of policy gradient RL.

Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tasks by building upon prior knowledge. However, current lifelong learning methods exhibit non-vanishing regret as the amount of experience increases, and include limitations that can lead to suboptimal or unsafe control policies. To address these issues, we develop a lifelong policy gradient learner that operates in an adversarial setting to learn multiple tasks online while enforcing safety constraints on the learned policies. We demonstrate, for the first time, sublinear regret for lifelong policy search, and validate our algorithm on several benchmark dynamical systems and an application to quadrotor control.

This paper develops an efficient online algorithm for learning multiple consecutive tasks based on the K-SVD algorithm for sparse dictionary optimization. We first derive a batch multi-task learning method that builds upon K-SVD, and then extend the batch algorithm to train models online in a lifelong learning setting. The resulting method has lower computational complexity than other current lifelong learning algorithms while maintaining nearly identical model performance. Additionally, the proposed method offers an alternate formulation for lifelong learning that supports both task and feature similarity matrices.

We develop an online multi-task formulation of model-based gradient temporal-difference (GTD) reinforcement learning. Our approach enables an autonomous RL agent to accumulate knowledge over its lifetime and efficiently share this knowledge between tasks to accelerate learning. Rather than learning a policy for a reinforcement learning task tabula rasa, as in standard GTD, our approach rapidly learns a high performance policy by building upon the agent's previously learned knowledge. Our preliminary results on controlling different mountain car tasks demonstrates that GTD-ELLA significantly improves learning over standard GTD(0).

Policy gradient algorithms have shown considerable recent success in solving high-dimensional sequential decision making tasks, particularly in robotics. However, these methods often require extensive experience in a domain to achieve high performance. To make agents more sample-efficient, we developed a multi-task policy gradient method to learn decision making tasks consecutively, transferring knowledge between tasks to accelerate learning. Our approach provides robust theoretical guarantees, and we show empirically that it dramatically accelerates learning on a variety of dynamical systems, including an application to quadrotor control.

In a lifelong learning framework, an agent acquires knowledge incrementally over consecutive learning tasks, continually building upon its experience. Recent lifelong learning algorithms have achieved nearly identical performance to batch multi-task learning methods while reducing learning time by three orders of magnitude. In this paper, we further improve the scalability of lifelong learning by developing curriculum selection methods that enable an agent to actively select the next task to learn in order to maximize performance on future learning tasks. We demonstrate that active task selection is highly reliable and effective, allowing an agent to learn high performance models using up to 50% fewer tasks than when the agent has no control over the task order. We also explore a variant of transfer learning in the lifelong learning setting in which the agent can focus knowledge acquisition toward a particular target task.

The problem of learning multiple consecutive tasks, known as lifelong learning, is of great importance to the creation of intelligent, general-purpose, and flexible machines. In this paper, we develop a method for online multi-task learning in the lifelong learning setting. The proposed Efficient Lifelong Learning Algorithm (ELLA) maintains a sparsely shared basis for all task models, transfers knowledge from the basis to learn each new task, and refines the basis over time to maximize performance across all tasks. We show that ELLA has strong connections to both online dictionary learning for sparse coding and state-of-the-art batch multi-task learning methods, and provide robust theoretical performance guarantees. We show empirically that ELLA yields nearly identical performance to batch multi-task learning while learning tasks sequentially in three orders of magnitude (over 1,000x) less time.

Current modularity-based community detection methods show decreased performance as relational networks become increasingly noisy. These methods also yield a large number of diverse community structures as solutions, which is problematic for applications that impose constraints on the acceptable solutions or in cases where the user is focused on specific communities of interest. To address both of these problems, we develop a semi-supervised spin-glass model that enables current community detection methods to incorporate background knowledge in the forms of individual labels and pairwise constraints. Unlike current methods, our approach shows robust performance in the presence of noise in the relational network, and the ability to guide the discovery process toward specific community structures. We evaluate our algorithm on several benchmark networks and a new political sentiment network representing cooperative events between nations that was mined from news articles over six years.

The success of transfer learning on a target task is highly dependent on the selected source data. Instance transfer methods reuse data from the source tasks to augment the training data for the target task. If poorly chosen, this source data may inhibit learning, resulting in negative transfer. The current most widely used algorithm for instance transfer, TrAdaBoost, performs poorly when given irrelevant source data. We present a novel task-based boosting technique for instance transfer that selectively chooses the source knowledge to transfer to the target task. Our approach performs boosting at both the instance level and the task level, assigning higher weight to those source tasks that show positive transferability to the target task, and adjusting the weights of individual instances within each source task via AdaBoost. We show that this combination of task- and instance-level boosting significantly improves transfer performance over existing instance transfer algorithms when given a mix of relevant and irrelevant source data, especially for small amounts of data on the target task.

We present an interactive learning method that enables a user to iteratively refine a regression model. The user examines the output of the model, visualized as the vertical axis of a 2D scatterplot, and provides corrections by repositioning individual data instances to the correct output level. Each repositioned data instance acts as a control point for altering the learned model, using the geometry underlying the data. We capture the underlying structure of the data as a manifold, on which we compute a set of basis functions as the foundation for learning. Our results show that manifold-based interactive learning improves performance monotonically with each correction, outperforming alternative approaches.

Multi-view learning algorithms typically assume a complete bipartite mapping between the different views in order to exchange information during the learning process. However, many applications provide only a partial mapping between the views, creating a challenge for current methods. To address this problem, we propose a multi-view algorithm based on constrained clustering that can operate with an incomplete mapping. Given a set of pairwise constraints in each view, our approach propagates these constraints using a local similarity measure to those instances that can be mapped to the other views, allowing the propagated constraints to be transferred across views via the partial mapping. It uses co-EM to iteratively estimate the propagation within each view based on the current clustering model, transfer the constraints across views, and update the clustering model, thereby learning a unified model for all views. We show that this approach significantly improves clustering performance over several other methods for transferring constraints and allows multi-view clustering to be reliably applied when given a limited mapping between the views.

Although there has been significant research on modelling and learning user preferences for various types of objects, there has been relatively little work on the problem of representing and learning preferences over sets of objects. We introduce a representation language, DD-PREF, that balances preferences for particular objects with preferences about the properties of the set. Specifically, we focus on the depth of objects (i.e. preferences for specific attribute values over others) and on the diversity of sets (i.e. preferences for broad vs. narrow distributions of attribute values). The DD-PREF framework is general and can incorporate additional object- and set-based preferences. We describe a greedy algorithm, DD-Select, for selecting satisfying sets from a collection of new objects, given a preference in this language. We show how preferences represented in DD-PREF can be learned from training data. Experimental results are given for three domains: a blocks world domain with several different task-based preferences, a real-world music playlist collection, and rover image data gathered in desert training exercises.

Most work on preference learning has focused on pairwise preferences or rankings over individual items. In this paper, we present a method for learning preferences over sets of items. Our learning method takes as input a collection of positive examples---that is, one or more sets that have been identified by a user as desirable. Kernel density estimation is used to estimate the value function for individual items, and the desired set diversity is estimated from the average set diversity observed in the collection. Since this is a new learning problem, we introduce a new evaluation methodology and evaluate the learning method on two data collections: synthetic blocks-world data and a new real-world music data collection that we have gathered.