Tejas Vaidhya, Ayush Kaushal, Vineet Jain, Francis Couture-Harpin, Prashant Shishodia, Majid Behbahani, Yuriy Nevmyvaka, Irina Rish. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

The Momentum Schr{ö}dinger Bridge (mSB) (Chen et al., 2023c) has emerged as a leading method for accelerating generative diffusion processes and reducing transport costs. However, the lack of simulation-free properties inevitably results in high training costs and affects scalability. To obtain a trade-off between transport properties and scalability, we introduce variational Schrödinger momentum diffusion (VSMD), which employs linearized forward score functions (variational scores) to eliminate the dependence on simulated forward trajectories. Our approach leverages a multivariate diffusion process with adaptively transport-optimized variational scores. Additionally, we apply a critical-damping transform to stabilize training by removing the need for score estimations for both velocity and samples. Theoretically, we prove the convergence of samples generated with optimal variational scores and momentum diffusion. Empirical results demonstrate that VSMD efficiently generates anisotropic shapes while maintaining transport efficacy, outperforming overdamped alternatives, and avoiding complex denoising processes. Our approach also scales effectively to real-world data, achieving competitive results in time series and image generation, both in unconditional and conditional settings.

We study differentially private algorithms for graph cut sparsification, a fundamental problem in algorithms, privacy, and machine learning. While significant progress has been made, the best-known private and efficient cut sparsifiers on $n$-node graphs approximate each cut within $\widetilde{O}(n^{1.5})$ additive error and $1+\gamma$ multiplicative error for any $\gamma > 0$ [Gupta, Roth, Ullman TCC'12]. In contrast, \emph{inefficient} algorithms, i.e., those requiring exponential time, can achieve an $\widetilde{O}(n)$ additive error and $1+\gamma$ multiplicative error [Eliáš, Kapralov, Kulkarni, Lee SODA'20]. In this work, we break the $n^{1.5}$ additive error barrier for private and efficient cut sparsification. We present an $(\varepsilon,\delta)$-DP polynomial time algorithm that, given a non-negative weighted graph, outputs a private synthetic graph approximating all cuts with multiplicative error $1+\gamma$ and additive error $n^{1.25 + o(1)}$ (ignoring dependencies on $\varepsilon, \delta, \gamma$). At the heart of our approach lies a private algorithm for expander decomposition, a popular and powerful technique in (non-private) graph algorithms.

Many forms of sensitive data, such as web traffic, mobility data, or hospital occupancy, are inherently sequential. The standard method for training machine learning models while ensuring privacy for units of sensitive information, such as individual hospital visits, is differentially private stochastic gradient descent (DP-SGD). However, we observe in this work that the formal guarantees of DP-SGD are incompatible with time series specific tasks like forecasting, since they rely on the *privacy amplification* attained by training on small, unstructured batches sampled from an unstructured dataset. In contrast, batches for forecasting are generated by (1) sampling sequentially structured time series from a dataset, (2) sampling contiguous subsequences from these series, and (3) partitioning them into context and ground-truth forecast windows. We theoretically analyze the privacy amplification attained by this *structured subsampling* to enable the training of forecasting models with sound and tight event- and user-level privacy guarantees. Towards more private models, we additionally prove how data augmentation amplifies privacy in self-supervised training of sequence models. Our empirical evaluation demonstrates that amplification by structured subsampling enables the training of forecasting models with strong formal privacy guarantees.

Multi-modal time series analysis has recently emerged as a prominent research area, driven by the increasing availability of diverse data modalities, such as text, images, and structured tabular data from real-world sources. However, effective analysis of multi-modal time series is hindered by data heterogeneity, modality gap, misalignment, and inherent noise. Recent advancements in multi-modal time series methods have exploited the multi-modal context via cross-modal interactions based on deep learning methods, significantly enhancing various downstream tasks. In this tutorial and survey, we present a systematic and up-to-date overview of multi-modal time series datasets and methods. We first state the existing challenges of multi-modal time series analysis and our motivations, with a brief introduction of preliminaries. Then, we summarize the general pipeline and categorize existing methods through a unified cross-modal interaction framework encompassing fusion, alignment, and transference at different levels (i.e., input, intermediate, output), where key concepts and ideas are highlighted. We also discuss the real-world applications of multi-modal analysis for both standard and spatial time series, tailored to general and specific domains. Finally, we discuss future research directions to help practitioners explore and exploit multi-modal time series. The up-to-date resources are provided in the GitHub repository. https://github.com/UConn-DSIS/Multi-modal-Time-Series-Analysis.

Time series data is now pervasive across domains such as healthcare, finance, entertainment, and transportation, driven by advances in sensing technologies that enable continuous data collection. The resulting increase in data volume and complexity poses significant challenges to traditional analysis methods, calling for the development of advanced, interdisciplinary approaches to temporal data mining. This workshop aims to: (1) identify key challenges in learning from time series data, including irregular sampling, spatiotemporal dependencies, and uncertainty quantification; (2) explore recent advances in algorithmic, statistical, theoretical, and systems-based solutions-ranging from classical methods to emerging techniques involving large language models (LLMs); and (3) foster collaboration by highlighting open problems and novel research directions in time series analysis. Bridging theory and practice, the workshop provides a platform for researchers and practitioners from academia, industry, and government to exchange ideas, discuss technical challenges, and showcase practical applications. Contributions from related areas such as AI, machine learning, data science, and statistics are strongly encouraged.

Given an undirected, weighted $n$-vertex graph $G = (V, E, w)$, a Gomory-Hu tree $T$ is a weighted tree on $V$ that preserves the Min-$s$-$t$-Cut between any pair of vertices $s, t \in V$. Finding cuts in graphs is a key primitive in problems such as bipartite matching, spectral and correlation clustering, and community detection. We design a differentially private (DP) algorithm that computes an approximate Gomory-Hu tree. Our algorithm is $\varepsilon$-DP, runs in polynomial time, and can be used to compute $s$-$t$ cuts that are $\tilde{O}(n/\varepsilon)$-additive approximations of the Min-$s$-$t$-Cuts in $G$ for all distinct $s, t \in V$ with high probability. Our error bound is essentially optimal, since [Dalirrooyfard, Mitrovic and Nevmyvaka, Neurips 2023] showed that privately outputting a single Min-$s$-$t$-Cut requires $\Omega(n)$ additive error even with $(\varepsilon, \delta)$-DP and allowing for multiplicative error. Prior to our work, the best additive error bounds for approximate all-pairs Min-$s$-$t$-Cuts were $O(n^{3/2}/\varepsilon)$ for $\varepsilon$-DP [Gupta, Roth, Ullman, TCC 2009] and $\tilde{O}(\sqrt{mn}/ \varepsilon)$ for $(\varepsilon, \delta)$-DP [Liu, Upadhyay and Zou, SODA 2024], both achieved by DP algorithms that preserve all cuts in the graph. To achieve our result, we develop an $\varepsilon$-DP algorithm for the Minimum Isolating Cuts problem with near-linear error, and introduce a novel privacy composition technique combining elements of both parallel and basic composition to handle `bounded overlap' computational branches in recursive algorithms, which maybe of independent interest.

Large Language Models (LLMs) and Foundation Models (FMs) have recently become prevalent for time series forecasting tasks. While fine-tuning LLMs enables domain adaptation, they often struggle to generalize across diverse and unseen datasets. Moreover, existing Time Series Foundation Models (TSFMs) still face challenges in handling non-stationary dynamics and distribution shifts, largely due to the lack of effective mechanisms for adaptation. To this end, we present TS-RAG, a retrieval-augmented generation framework for time series forecasting that enhances the generalization and interpretability of TSFMs. Specifically, TS-RAG leverages pre-trained time series encoders to retrieve semantically relevant segments from a dedicated knowledge base, enriching the contextual representation of the input query. Furthermore, we propose an Adaptive Retrieval Mixer (ARM) module that dynamically fuses the retrieved patterns with the TSFM's internal representation, improving forecasting accuracy without requiring task-specific fine-tuning. Thorough empirical studies on seven public benchmark datasets demonstrate that TS-RAG achieves state-of-the-art zero-shot forecasting performance, outperforming the existing TSFMs by up to 6.84\% across diverse domains while also providing desirable interpretability. Our code and data are available at: https://github.com/UConn-DSIS/TS-RAG.

In many real world networks, there already exists a (not necessarily optimal) $k$-partitioning of the network. Oftentimes, for such networks, one aims to find a $k$-partitioning with a smaller cut value by moving only a few nodes across partitions. The number of nodes that can be moved across partitions is often a constraint forced by budgetary limitations. Motivated by such real-world applications, we introduce and study the $r$-move $k$-partitioning problem, a natural variant of the Multiway cut problem. Given a graph, a set of $k$ terminals and an initial partitioning of the graph, the $r$-move $k$-partitioning problem aims to find a $k$-partitioning with the minimum-weighted cut among all the $k$-partitionings that can be obtained by moving at most $r$ non-terminal nodes to partitions different from their initial ones. Our main result is a polynomial time $3(r+1)$ approximation algorithm for this problem. We further show that this problem is $W[1]$-hard, and give an FPTAS for when $r$ is a small constant.

Probabilistic time series forecasting is a challenging problem due to the long sequences involved, the large number of samples needed for accurate probabilistic inference, and the need for real-time inference in many applications. These challenges necessitate methods that are not only accurate but computationally efficient. Unfortunately, most current state-of-the-art methods for time series forecasting are based on Transformers, which scale poorly due to quadratic complexity in sequence length, and are therefore needlessly computationally inefficient. Moreover, with a few exceptions, these methods have only been evaluated for non-probabilistic point estimation. In this work, we address these two shortcomings. For the first, we introduce VQ-TR, which maps large sequences to a discrete set of latent representations as part of the Attention module. This not only allows us to attend over larger context windows with linear complexity in sequence length but also allows for effective regularization to avoid overfitting. For the second, we provide what is to the best of our knowledge the first systematic comparison of modern Transformer-based time series forecasting methods for probabilistic forecasting. In this comparison, we find that VQ-TR performs better or comparably to all other methods while being computationally efficient.

Schrödinger bridge (SB) has emerged as the go-to method for optimizing transportation plans in diffusion models. However, SB requires estimating the intractable forward score functions, inevitably resulting in the (costly) implicit training loss based on simulated trajectories. To improve the scalability while preserving efficient transportation plans, we leverage variational inference to linearize the forward score functions (variational scores) of SB and restore *simulation-free* properties in training backward scores. We propose the variational Schrödinger diffusion model (VSDM), where the forward process is a multivariate diffusion and the variational scores are adaptively optimized for efficient transport. Theoretically, we use stochastic approximation to prove the convergence of the variational scores and show the convergence of the adaptively generated samples based on the optimal variational scores. Empirically, we test the algorithm in simulated examples and observe that VSDM is efficient in generations of anisotropic shapes and yields straighter sample trajectories compared to the single-variate diffusion. We also verify the scalability of the algorithm in real-world data and achieve competitive unconditional generation performance in CIFAR10 and conditional generation in time series modeling. Notably, VSDM no longer depends on warm-up initializations required by SB.

Recently, there has been a growing interest in leveraging pre-trained large language models (LLMs) for various time series applications. However, the semantic space of LLMs, established through the pre-training, is still underexplored and may help yield more distinctive and informative representations to facilitate time series forecasting. To this end, we propose Semantic Space Informed Prompt learning with LLM ($S^2$IP-LLM) to align the pre-trained semantic space with time series embedding space and perform time series forecasting based on learned prompts from the joint space. We first design a tokenization module tailored for cross-modality alignment, which explicitly concatenates patches of decomposed time series components to create embeddings that effectively encode the temporal dynamics. Next, we leverage the pre-trained word token embeddings to derive semantic anchors and align selected anchors with time series embeddings by maximizing the cosine similarity in the joint space. This way, $S^2$IP-LLM can retrieve relevant semantic anchors as prompts to provide strong indicators (context) for time series that exhibit different temporal dynamics. With thorough empirical studies on multiple benchmark datasets, we demonstrate that the proposed $S^2$IP-LLM can achieve superior forecasting performance over state-of-the-art baselines. Furthermore, our ablation studies and visualizations verify the necessity of prompt learning informed by semantic space.

Time series data has become ubiquitous across various fields such as healthcare, finance, entertainment, and transportation, driven by advancements in sensing technologies that enable continuous monitoring and recording. This growth in data size and complexity presents new challenges for traditional analysis techniques, necessitating the development of advanced, interdisciplinary temporal mining algorithms. The goals of this workshop are to: (1) highlight significant challenges in learning and mining from time series data, such as irregular sampling, spatiotemporal structures, and uncertainty quantification; (2) discuss recent developments in algorithmic, theoretical, statistical, and systems-based approaches for addressing these challenges, including both classical methods and large language models (LLMs); and (3) synergize research efforts by exploring both new and open problems in time series analysis and mining. This workshop will focus on both the theoretical and practical aspects of time series data analysis, providing a platform for researchers and practitioners from academia, government, and industry to discuss potential research directions, critical technical issues, and present solutions for practical applications. Contributions from related fields such as AI, machine learning, data science, and statistics are also included.

Quantifying aleatoric uncertainty is a challenging task in machine learning. It is important for decision making associated with data-dependent uncertainty in model outcomes. Recently, many empirical studies in modeling aleatoric uncertainty under regression settings primarily rely on either a Gaussian likelihood or moment matching. However, the performance of these methods varies for different datasets whereas discussions on their theoretical guarantees are lacking. In this work, we investigate theoretical aspects of these approaches and establish risk bounds for their estimates. We provide conditions that are sufficient to guarantee the PAC-learnablility of the aleatoric uncertainty. The study suggests that the likelihood and moment matching-based methods enjoy different types of guarantee in their risk bounds, i.e., they calibrate different aspects of the uncertainty and thus exhibit distinct properties in different regimes of the parameter space. Finally, we conduct empirical study which shows promising results and supports our theorems.

Temporal data such as time series can be viewed as discretized measurements of the underlying function. To build a generative model for such data we have to model the stochastic process that governs it. We propose a solution by defining the denoising diffusion model in the function space which also allows us to naturally handle irregularly-sampled observations. The forward process gradually adds noise to functions, preserving their continuity, while the learned reverse process removes the noise and returns functions as new samples. To this end, we define suitable noise sources and introduce novel denoising and score-matching models. We show how our method can be used for multivariate probabilistic forecasting and imputation, and how our model can be interpreted as a neural process.

The Schrödinger bridge problem (SBP) is gaining increasing attention in generative modeling and showing promising potential even in comparison with the score-based generative models (SGMs). SBP can be interpreted as an entropy-regularized optimal transport problem, which conducts projections onto every other marginal alternatingly. However, in practice, only approximated projections are accessible and their convergence is not well understood. To fill this gap, we present a first convergence analysis of the Schrödinger bridge algorithm based on approximated projections. As for its practical applications, we apply SBP to probabilistic time series imputation by generating missing values conditioned on observed data. We show that optimizing the transport cost improves the performance and the proposed algorithm achieves the state-of-the-art result in healthcare and environmental data while exhibiting the advantage of exploring both temporal and feature patterns in probabilistic time series imputation.

Time series data has become pervasive across domains such as finance, transportation, retail, entertainment, and healthcare. This shift towards continuous monitoring and recording, fueled by advancements in sensing technologies, necessitates the development of new tools and solutions. Despite extensive study, the importance of time series analysis continues to increase. However, modern time series data present challenges to existing techniques, including irregular sampling and spatiotemporal structures. Time series mining research is both challenging and rewarding as it connects diverse disciplines and requires interdisciplinary solutions. The goals of this workshop are to (1) highlight the significant challenges that underpin learning and mining from time series data (e.g., irregular sampling, spatiotemporal structure, uncertainty quantification), (2) discuss recent algorithmic, theoretical, statistical, or systems-based developments for tackling these problems, and (3) to synergize the research activities and discuss both new and open problems in time series analysis and mining. In summary, our workshop will focus on both the theoretical and practical aspects of time series data analysis and will provide a platform for researchers and practitioners from academia and industry to discuss potential research directions and critical technical issues and present solutions to tackle related issues in practical applications. We will invite researchers and practitioners from the related areas of AI, machine learning, data science, statistics, and many others to contribute to this workshop.

Finding min $s$-$t$ cuts in graphs is a basic algorithmic tool, with applications in image segmentation, community detection, reinforcement learning, and data clustering. In this problem, we are given two nodes as terminals and the goal is to remove the smallest number of edges from the graph so that these two terminals are disconnected. We study the complexity of differential privacy for the min $s$-$t$ cut problem and show nearly tight lower and upper bounds where we achieve privacy at no cost for running time efficiency. We also develop a differentially private algorithm for the multiway $k$-cut problem, in which we are given $k$ nodes as terminals that we would like to disconnect. As a function of $k$, we obtain privacy guarantees that are exponentially more efficient than applying the advanced composition theorem to known algorithms for multiway $k$-cut. Finally, we empirically evaluate the approximation of our differentially private min $s$-$t$ cut algorithm and show that it almost matches the quality of the output of non-private ones.

Many kinds of simultaneously-observed event sequences exhibit mutually exciting or inhibiting patterns. Reliable detection of such temporal dependencies is crucial for scientific investigation. A common model is the Multivariate Hawkes Process (MHP), whose impact function naturally encodes a causal structure in Granger causality. However, the vast majority of existing methods use a transformed standard MHP intensity with a constant baseline, which may be inconsistent with real-world data. On the other hand, modeling irregular and unknown background dynamics directly is a challenge, as one struggles to distinguish the effect of mutual interaction from that of fluctuations in background dynamics. In this paper, we address the short-term temporal dependency detection issue. We show that maximum likelihood estimation (MLE) for cross-impact from MHP has an error that can not be eliminated, but may be reduced by an order of magnitude using a heterogeneous intensity not for the target HP but for the interacting HP. Then we propose a robust and computationally-efficient modification of MLE that does not rely on the prior estimation of the heterogeneous intensity and is thus applicable in a data-limited regime (e.g., few-shot, unrepeated observations). Extensive experiments on various datasets show that our method outperforms existing ones by notable margins, with highlighted novel applications in neuroscience.

Detecting out-of-distribution (OOD) samples is a problem of practical importance for a reliable use of deep neural networks (DNNs) in production settings. The corollary to this problem is the detection in-distribution (ID) samples, which is applicable to domain adaptation scenarios for augmenting a train set with ID samples from other data sets, or to continual learning for replay from the past. For both ID or OOD detection, we propose a principled yet simple approach of (empirically) estimating KL-Divergence, in its dual form, for a given test set w.r.t. a known set of ID samples in order to quantify the contribution of each test sample individually towards the divergence measure and accordingly detect it as OOD or ID. Our approach is compute-efficient and enjoys strong theoretical guarantees. For WideResnet101 and ViT-L-16, by considering ImageNet-1k dataset as the ID benchmark, we evaluate the proposed OOD detector on 51 test (OOD) datasets, and observe drastically and consistently lower false positive rates w.r.t. all the competitive methods. Moreover, the proposed ID detector is evaluated, using ECG and stock price datasets, for the task of data augmentation in domain adaptation and continual learning settings, and we observe higher efficacy compared to relevant baselines.

Information-theoretic clustering is one of the most promising and principled approaches to finding clusters with minimal apriori assumptions. The key criterion therein is to maximize the mutual information between the data points and their cluster labels. Such an approach, however, does not explicitly promote any type of inter-cluster behavior. We instead propose to maximize the Kullback-Leibler divergence between the underlying data distributions associated to clusters (referred to as cluster distributions). We show it to entail the mutual information criterion along with maximizing cross entropy between the cluster distributions. For practical efficiency, we propose to empirically estimate the objective of KL-D between clusters in its dual form leveraging deep neural nets as a dual function approximator. Remarkably, our theoretical analysis establishes that estimating the divergence measure in its dual form simplifies the problem of clustering to one of optimally finding k-1 cut points for k clusters in the 1-D dual functional space. Overall, our approach enables linear-time clustering algorithms with theoretical guarantees of near-optimality, owing to the submodularity of the objective. We show the empirical superiority of our approach w.r.t. current state-of-the-art methods on the challenging task of clustering noisy timeseries as observed in domains such as neuroscience, healthcare, financial markets, spatio-temporal environmental dynamics, etc.

Time series data are ubiquitous, and is one of the fastest growing and richest types of data. Recent advances in sensing technologies has resulted in a rapid growth in the size and complexity of time series archives. This demands development of new tools and solutions. The goals of this workshop are to: (1) highlight the significant challenges that underpin learning and mining from time series data (e.g. irregular sampling, spatiotemporal structure, uncertainty quantification), (2) discuss recent algorithmic, theoretical, statistical, or systems-based developments for tackling these problems, and (3) exploring new frontiers in time series analysis and their connections with important topics such as knowledge representation, reasoning, control, and business intelligence. In summary, our workshop will focus on both the theoretical and practical aspects of time series data analysis and will provide a platform for researchers and practitioners from both academia and industry to discuss potential research directions, key technical issues, and present solutions to tackle related issues in practical applications. We will invite researchers and practitioners from the related areas of AI, machine learning, data science, statistics, and many others to contribute to this workshop.

Estimating Transfer Entropy (TE) between time series is a highly impactful problem in fields such as finance and neuroscience. The well-known nearest neighbor estimator of TE potentially fails if temporal dependencies are noisy and long ranged, primarily because it estimates TE indirectly relying on the estimation of joint entropy terms in high dimensions, which is a hard problem in itself. Other estimators, such as those based on Copula entropy or conditional mutual information have similar limitations. Leveraging the successes of modern discriminative models that operate in high dimensional (noisy) feature spaces, we express TE as a difference of two conditional entropy terms, which we directly estimate from conditional likelihoods computed in-sample from any discriminator (timeseries forecaster) trained per maximum likelihood principle. To ensure that the in-sample log likelihood estimates are not overfit to the data, we propose a novel perturbation model based on locality sensitive hash (LSH) functions, which regularizes a discriminative model to have smooth functional outputs within local neighborhoods of the input space. Our estimator is consistent, and its variance reduces linearly in sample size. We also demonstrate its superiority w.r.t. state-of-the-art estimators through empirical evaluations on a synthetic as well as real world datasets from the neuroscience and finance domains.

We propose a state-based variant of the classical online learning problem of tracking the best expert. In our setting, the actions of the algorithm and experts correspond to local moves through a continuous and bounded state space. At each step, Nature chooses payoffs as a function of each player’s current position and action. Our model therefore integrates the problem of prediction with expert advice with the stateful formalisms of reinforcement learning. Traditional no-regret learning approaches no longer apply, but we propose a simple algorithm that provably achieves no-regret when the state space is any convex Euclidean region. Our algorithm combines techniques from online learning with results from the literature on pursuit-evasion games. We describe a quantitative trading application in which the convex region captures inventory risk constraints, and local moves limit market impact. Using historical market data, we show experimentally that our algorithm has a strong advantage over classic no-regret approaches.

We present the first large-scale empirical application of reinforcement learning to the important problem of optimized trade execution in modern financial markets. Our experiments are based on 1.5 years of millisecond time-scale limit order data from NASDAQ, and demonstrate the promise of reinforcement learning methods to market microstructure problems. Our learning algorithm introduces and exploits a natural "low-impact " factorization of the state space. 1.