Zero-sum stochastic games have found important applications in a variety of fields, from machine learning to economics. Work on this model has primarily focused on the computation of Nash equilibrium due to its effectiveness in solving adversarial board and video games. Unfortunately, a Nash equilibrium is not guaranteed to exist in zero-sum stochastic games when the payoffs at each state are not convex-concave in the players' actions. A Stackelberg equilibrium, however, is guaranteed to exist. Consequently, in this paper, we study zero-sum stochastic Stackelberg games. Going beyond known existence results for (non-stationary) Stackelberg equilibria, we prove the existence of recursive (i.e., Markov perfect) Stackelberg equilibria (recSE) in these games, provide necessary and sufficient conditions for a policy profile to be a recSE, and show that recSE can be computed in (weakly) polynomial time via value iteration. Finally, we show that zero-sum stochastic Stackelberg games can model the problem of pricing and allocating goods across agents and time. More specifically, we propose a zero-sum stochastic Stackelberg game whose recSE correspond to the recursive competitive equilibria of a large class of stochastic Fisher markets. We close with a series of experiments that showcase how our methodology can be used to solve the consumption-savings problem in stochastic Fisher markets.

Two key challenges facing modern deep learning is mitigating deep networks vulnerability to adversarial attacks, and understanding deep learning's generalization capabilities. Towards the first issue, many defense strategies have been developed, with the most common being Adversarial Training (AT). Towards the second challenge, one of the dominant theories that has emerged is the Neural Tangent Kernel (NTK) -- a characterization of neural network behavior in the infinite-width limit. In this limit, the kernel is frozen and the underlying feature map is fixed. In finite-widths however, there is evidence that feature learning happens at the earlier stages of the training (kernel learning) before a second phase where the kernel remains fixed (lazy training).

We study acquisition functions for active learning (AL) for text classification. The Expected Loss Reduction (ELR) method focuses on a Bayesian estimate of the reduction in classification error, recently updated with Mean Objective Cost of Uncertainty (MOCU). We convert the ELR framework to estimate the increase in (strictly proper) scores like log probability or negative mean square error, which we call Bayesian Estimate of Mean Proper Scores (BEMPS). We also prove convergence results borrowing techniques used with MOCU. In order to allow better experimentation with the new acquisition functions, we develop a complementary batch AL algorithm, which encourages diversity in the vector of expected changes in scores for unlabelled data. To allow high performance text classifiers, we combine ensembling and dynamic validation set construction on pretrained language models. Extensive experimental evaluation then explores how these different acquisition functions perform. The results show that the use of mean square error and log probability with BEMPS yields robust acquisition functions, which consistently outperform the others tested.

Class-incremental learning (CIL) learns a classification model with training data of different classes arising progressively. Existing CIL either suffers from serious accuracy loss due to catastrophic forgetting, or invades data privacy by revisiting used exemplars. Inspired by learning of linear problems, we propose an analytic class-incremental learning (ACIL) with absolute memorization of past knowledge while avoiding breaching of data privacy (i.e., without storing historical data). The absolute memorization is demonstrated in the sense that the CIL using ACIL given present data would give identical results to that from its joint-learning counterpart that consumes both present and historical samples. This equality is theoretically validated. The data privacy is ensured by showing that no historical data are involved during the learning process. Empirical validations demonstrate ACIL's competitive accuracy performance with near-identical results for various incremental task settings (e.g., 5-50 phases). This also allows ACIL to outperform the state-of-the-art methods for large-phase scenarios (e.g., 25 and 50 phases).

Reinforcement learning agents deployed in the real world often have to cope with partially observable environments. Therefore, most agents employ memory mechanisms to approximate the state of the environment. Recently, there have been impressive success stories in mastering partially observable environments, mostly in the realm of computer games like Dota 2, StarCraft II, or MineCraft. However, existing methods lack interpretability in the sense that it is not comprehensible for humans what the agent stores in its memory.In this regard, we propose a novel memory mechanism that represents past events in human language.Our method uses CLIP to associate visual inputs with language tokens. Then we feed these tokens to a pretrained language model that serves the agent as memory and provides it with a coherent and human-readable representation of the past.We train our memory mechanism on a set of partially observable environments and find that it excels on tasks that require a memory component, while mostly attaining performance on-par with strong baselines on tasks that do not. On a challenging continuous recognition task, where memorizing the past is crucial, our memory mechanism converges two orders of magnitude faster than prior methods.Since our memory mechanism is human-readable, we can peek at an agent's memory and check whether crucial pieces of information have been stored.This significantly enhances troubleshooting and paves the way toward more interpretable agents.

Active Learning (AL) aims to reduce the labeling burden by interactively selecting the most informative samples from a pool of unlabeled data. While there has been extensive research on improving AL query methods in recent years, some studies have questioned the effectiveness of AL compared to emerging paradigms such as semi-supervised (Semi-SL) and self-supervised learning (Self-SL), or a simple optimization of classifier configurations. Thus, today's AL literature presents an inconsistent and contradictory landscape, leaving practitioners uncertain about whether and how to use AL in their tasks. In this work, we make the case that this inconsistency arises from a lack of systematic and realistic evaluation of AL methods. Specifically, we identify five key pitfalls in the current literature that reflect the delicate considerations required for AL evaluation. Further, we present an evaluation framework that overcomes these pitfalls and thus enables meaningful statements about the performance of AL methods. To demonstrate the relevance of our protocol, we present a large-scale empirical study and benchmark for image classification spanning various data sets, query methods, AL settings, and training paradigms. Our findings clarify the inconsistent picture in the literature and enable us to give hands-on recommendations for practitioners.

It is well-known that modern computer vision systems often exhibit behaviors misaligned with those of humans: from adversarial attacks to image corruptions, deeplearning vision models suffer in a variety of settings that humans capably handle. Inlight of these phenomena, here we introduce another, orthogonal perspective studying the human-machine vision gap.

To improve the sustainability and resilience of modern food systems, designing improved crop management strategies is crucial. The increasing abundance of data on agricultural systems suggests that future strategies could benefit from adapting to environmental conditions, but how to design these adaptive policies poses a new frontier. A natural technique for learning policies in these kinds of sequential decision-making problems is reinforcement learning (RL). To obtain the large number of samples required to learn effective RL policies, existing work has used mechanistic crop growth models (CGMs) as simulators. These solutions focus on single-year, single-crop simulations for learning strategies for a single agricultural management practice. However, to learn sustainable long-term policies we must be able to train in multi-year environments, with multiple crops, and consider a wider array of management techniques.

Text-conditioned image editing has emerged as a powerful tool for editing images.However, in many situations, language can be ambiguous and ineffective in describing specific image edits.When faced with such challenges, visual prompts can be a more informative and intuitive way to convey ideas.We present a method for image editing via visual prompting.Given pairs of example that represent the before and after images of an edit, our goal is to learn a text-based editing direction that can be used to perform the same edit on new images.We leverage the rich, pretrained editing capabilities of text-to-image diffusion models by inverting visual prompts into editing instructions.Our results show that with just one example pair, we can achieve competitive results compared to state-of-the-art text-conditioned image editing frameworks.

Much of sensory neuroscience focuses on sensory features that are chosen by the experimenter because they are thought to be behaviorally relevant to the organism. However, it is not generally known what these features are in complex, natural scenes. This work focuses on using the retinal encoding of natural movies to determine the presumably behaviorally-relevant features that the brain represents. It is prohibitive to parameterize a natural movie and its respective retinal encoding fully. We use time within a natural movie as a proxy for the whole suite of features evolving across the scene.