A threshold key encapsulation mechanism (TKEM) facilitates the secure distribution of session keys among multiple participants, allowing key recovery through a threshold number of shares. TKEM has gained significant attention, especially for decentralized systems, including blockchains. However, existing constructions often rely on trusted setups, which pose security risks such as a single point of failure and are limited by fixed participant numbers and thresholds. To overcome this issue, we propose a dynamic TKEM with a transparent setup, allowing for a flexible selection of both recipients and thresholds without relying on trusted third parties in the setup phase. In addition, our construction does not rely on pairing operations, which are less efficient compared to exponentiation. We prove the selective chosen-ciphertext security of our construction under the decisional Diffie-Hellman assumption, zero-knowledge, and soundness of a non-interactive zero-knowledge (NIZK) proof system. We also show that our scheme satisfies decapsulation consistency when the underlying NIZK system is sound. Our proof-of-concept implementation highlights the practicality and efficiency of this approach, further advancing the field of threshold cryptography.

Saliency methods are a popular class of feature attribution explanation methods that aim to capture a model’s predictive reasoning by identifying "important" pixels in an input image. However, the development and adoption of these methods are hindered by the lack of access to ground-truth model reasoning, which prevents accurate evaluation. In this work, we design a synthetic benchmarking framework, SMERF, that allows us to perform ground-truth-based evaluation while controlling the complexity of the model’s reasoning. Experimentally, SMERF reveals significant limitations in existing saliency methods and, as a result, represents a useful tool for the development of new saliency methods.

When subjected to automated decision-making, decision subjects may strategically modify their observable features in ways they believe will maximize their chances of receiving a favorable decision. In many practical situations, the underlying assessment rule is deliberately kept secret to avoid gaming and maintain competitive advantage. The resulting opacity forces the decision subjects to rely on incomplete information when making strategic feature modifications. We capture such settings as a game of Bayesian persuasion, in which the decision maker offers a form of recourse to the decision subject by providing them with an action recommendation (or signal) to incentivize them to modify their features in desirable ways. We show that when using persuasion, the decision maker and decision subject are never worse off in expectation, while the decision maker can be significantly better off. While the decision maker’s problem of finding the optimal Bayesian incentive compatible (BIC) signaling policy takes the form of optimization over infinitely many variables, we show that this optimization can be cast as a linear program over finitely-many regions of the space of possible assessment rules. While this reformulation simplifies the problem dramatically, solving the linear program requires reasoning about exponentially-many variables, even in relatively simple cases. Motivated by this observation, we provide a polynomial-time approximation scheme that recovers a near-optimal signaling policy. Finally, our numerical simulations on semi-synthetic data empirically demonstrate the benefits of using persuasion in the algorithmic recourse setting.

Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a necessary cost in loss of model’s predictive performance. We propose a general diagnostic that enables systematic characterization of these trade-offs in group fairness. We observe that the majority of group fairness notions can be expressed via the fairness-confusion tensor, which is the confusion matrix split according to the protected attribute values. We frame several optimization problems that directly optimize both accuracy and fairness objectives over the elements of this tensor, which yield a general perspective for understanding multiple trade-offs including group fairness incompatibilities. It also suggests an alternate post-processing method for designing fair classifiers. On synthetic and real datasets, we demonstrate the use cases of our diagnostic, particularly on understanding the trade-off landscape between accuracy and fairness.

We propose PLLay, a novel topological layer for general deep learning models based on persistence landscapes, in which we can efficiently exploit the underlying topological features of the input data structure. In this work, we show differentiability with respect to layer inputs, for a general persistent homology with arbitrary filtration. Thus, our proposed layer can be placed anywhere in the network and feed critical information on the topological features of input data into subsequent layers to improve the learnability of the networks toward a given task. A task-optimal structure of PLLay is learned during training via backpropagation, without requiring any input featurization or data preprocessing. We provide a novel adaptation for the DTM function-based filtration, and show that the proposed layer is robust against noise and outliers through a stability analysis. We demonstrate the effectiveness of our approach by classification experiments on various datasets.

In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to validate various qualitative properties of a model. Partial dependence plots (PDP), including instance-specific PDPs (i.e., ICE plots), have been widely used as a visual tool to understand or validate a model. Yet, current PDPs suffer from two main drawbacks: (1) a user must manually sort or select interesting plots, and (2) PDPs are usually limited to plots along a single feature. To address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw feature space or a latent space arising from some generative model. We demonstrate the usefulness of our automated dependence plots (ADP) across multiple use-cases and datasets including model selection, bias detection, understanding out-of-sample behavior, and exploring the latent space of a generative model. The code is available at . Cite this Paper BibTeX @InProceedings{pmlr-v124-inouye20a, title = {Automated Dependence Plots}, author = {Inouye, David and Leqi, Liu and Sik Kim, Joon and Aragam, Bryon and Ravikumar, Pradeep}, booktitle = {Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI)}, pages = {1238--1247}, year = {2020}, editor = {Peters, Jonas and Sontag, David}, volume = {124}, series = {Proceedings of Machine Learning Research}, month = {03--06 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v124/inouye20a/inouye20a.pdf}, url = {https://proceedings.mlr.press/v124/inouye20a.html}, abstract = {In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to validate various qualitative properties of a model. Partial dependence plots (PDP), including instance-specific PDPs (i.e., ICE plots), have been widely used as a visual tool to understand or validate a model. Yet, current PDPs suffer from two main drawbacks: (1) a user must manually sort or select interesting plots, and (2) PDPs are usually limited to plots along a single feature. To address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw feature space or a latent space arising from some generative model. We demonstrate the usefulness of our automated dependence plots (ADP) across multiple use-cases and datasets including model selection, bias detection, understanding out-of-sample behavior, and exploring the latent space of a generative model. The code is available at .} } Copy to Clipboard Download Endnote %0 Conference Paper %T Automated Dependence Plots %A David Inouye %A Liu Leqi %A Joon Sik Kim %A Bryon Aragam %A Pradeep Ravikumar %B Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI) %C Proceedings of Machine Learning Research %D 2020 %E Jonas Peters %E David Sontag %F pmlr-v124-inouye20a %I PMLR %P 1238--1247 %U https://proceedings.mlr.press/v124/inouye20a.html %V 124 %X In practical applications of machine learning, it is necessary to look beyond standard metrics such as test accuracy in order to validate various qualitative properties of a model. Partial dependence plots (PDP), including instance-specific PDPs (i.e., ICE plots), have been widely used as a visual tool to understand or validate a model. Yet, current PDPs suffer from two main drawbacks: (1) a user must manually sort or select interesting plots, and (2) PDPs are usually limited to plots along a single feature. To address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw feature space or a latent space arising from some generative model. We demonstrate the usefulness of our automated dependence plots (ADP) across multiple use-cases and datasets including model selection, bias detection, understanding out-of-sample behavior, and exploring the latent space of a generative model. The code is available at . Copy to Clipboard Download APA Inouye, D., Leqi, L., Sik Kim, J., Aragam, B. & Ravikumar, P.. (2020). Automated Dependence Plots. Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence (UAI), in Proceedings of Machine Learning Research 124:1238-1247 Available from https://proceedings.mlr.press/v124/inouye20a.html. Copy to Clipboard Download Related Material Download PDF Supplementary PDF

This paper describes the Smart Survey Tool, a novel multi-device application for museum visitor tracking and tracking data visualization. The application allows museum staff to capture detailed information describing how visitors move around an exhibition and interact with individual exhibits. They can then visualize the results of tracking either on a single mobile device or with multiple mobile devices connected to a large display. The platform uses orthogonal views of the exhibition space for tracking and visualization, with a chess-piece icon to represent visitors during tracking, and curved semi-transparent lines with animated semi-circles to communicate the path and direction of visitor movement. Our visualization is novel in its use of an orthogonal projection for pedestrian tracking and animation to communicate the flow of visitors around the exhibition space, as well as allowing users to dynamically switch between views representing different groups of visitors. The design of our application was informed through an extensive requirements analysis study conducted with Nanjing Museum and evaluated by conducting expert interviews with museum managers who considered that the application allowed for more effective and efficient recording and analysis of visitor tracking data.

We propose to explain the predictions of a deep neural network, by pointing to the set of what we call representer points in the training set, for a given test point prediction. Specifically, we show that we can decompose the pre-activation prediction of a neural network into a linear combination of activations of training points, with the weights corresponding to what we call representer values, which thus capture the importance of that training point on the learned parameters of the network. But it provides a deeper understanding of the network than simply training point influence: with positive representer values corresponding to excitatory training points, and negative values corresponding to inhibitory points, which as we show provides considerably more insight. Our method is also much more scalable, allowing for real-time feedback in a manner not feasible with influence functions.

We tackle the problem of learning a rotation invariant latent factor model when the training data is comprised of lower-dimensional projections of the original feature space. The main goal is the discovery of a set of 3-D bases poses that can characterize the manifold of primitive human motions, or movemes, from a training set of 2-D projected poses obtained from still images taken at various camera angles. The proposed technique for basis discovery is data-driven rather than hand-designed. The learned representation is rotation invariant, and can reconstruct any training instance from multiple viewing angles. We apply our method to modeling human poses in sports (via the Leeds Sports Dataset), and demonstrate the effectiveness of the learned bases in a range of applications such as activity classification, inference of dynamics from a single frame, and synthetic representation of movements.