Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs

The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how to learn efficiently in a CMDP environment with a potentially infinite number of states remains under investigation, particularly when function approximation is applied to the value functions. In this paper, we address the learning problem given linear function approximation with $q_{\pi}$-realizability, where the value functions of all policies are linearly representable with a known feature map, a setting known to be more general and challenging than other linear settings. Utilizing a local-access model, we propose a novel primal-dual algorithm that, after $\tilde{O}(\text{poly}(d) \epsilon^{-3})$ queries, outputs with high probability a policy that strictly satisfies the constraints while nearly optimizing the value with respect to a reward function. Here, $d$ is the feature dimension and $\epsilon > 0$ is a given error. The algorithm relies on a carefully crafted off-policy evaluation procedure to evaluate the policy using historical data, which informs policy updates through policy gradients and conserves samples. To our knowledge, this is the first result achieving polynomial sample complexity for CMDP in the $q_{\pi}$-realizable setting.

Versatile Teacher: A Class-aware Teacher-student Framework for Cross-domain Adaptation

Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, has shown significant accuracy improvements. However, existing methods often overlook class differences, treating all classes equally, resulting in suboptimal results. Furthermore, the integration of instance-level alignment with a one-stage detector, essential due to the absence of a Region Proposal Network (RPN), remains unexplored in this framework. In response to these shortcomings, we introduce a novel teacher-student model named Versatile Teacher (VT). VT differs from previous works by considering class-specific detection difficulty and employing a two-step pseudo-label selection mechanism, referred to as Class-aware Pseudo-label Adaptive Selection (CAPS), to generate more reliable pseudo labels. These labels are leveraged as saliency matrices to guide the discriminator for targeted instance-level alignment. Our method demonstrates promising results on three benchmark datasets, and extends the alignment methods for widely-used one-stage detectors, presenting significant potential for practical applications. Code is available at https://github.com/RicardooYoung/VersatileTeacher.

A Robust ADMM-Based Optimization Algorithm For Underwater Acoustic Channel Estimation

Accurate estimation of the Underwater acoustic (UWA) is a key part of underwater communications, especially for coherent systems. The severe multipath effects and large delay spreads make the estimation problem large-scale. The non-stationary, non-Gaussian, and impulsive nature of ocean ambient noise poses further obstacles to the design of estimation algorithms. Under the framework of compressed sensing (CS), this work addresses the issue of robust channel estimation when measurements are contaminated by impulsive noise. A first-order algorithm based on alternating direction method of multipliers (ADMM) is proposed. Numerical simulations of time-varying channel estimation are performed to show its improved performance in highly impulsive noise environments.

Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions

Value iteration (VI) is a foundational dynamic programming method, important for learning and planning in optimal control and reinforcement learning. VI proceeds in batches, where the update to the value of each state must be completed before the next batch of updates can begin. Completing a single batch is prohibitively expensive if the state space is large, rendering VI impractical for many applications. Asynchronous VI helps to address the large state space problem by updating one state at a time, in-place and in an arbitrary order. However, Asynchronous VI still requires a maximization over the entire action space, making it impractical for domains with large action space. To address this issue, we propose doubly-asynchronous value iteration (DAVI), a new algorithm that generalizes the idea of asynchrony from states to states and actions. More concretely, DAVI maximizes over a sampled subset of actions that can be of any user-defined size. This simple approach of using sampling to reduce computation maintains similarly appealing theoretical properties to VI without the need to wait for a full sweep through the entire action space in each update. In this paper, we show DAVI converges to the optimal value function with probability one, converges at a near-geometric rate with probability 1-delta, and returns a near-optimal policy in computation time that nearly matches a previously established bound for VI. We also empirically demonstrate DAVI's effectiveness in several experiments.

Joint Adversarial Learning for Cross-domain Fair Classification

Modern machine learning (ML) models are becoming increasingly popular and are widely used in decision-making systems. However, studies have shown critical issues of ML discrimination and unfairness, which hinder their adoption on high-stake applications. Recent research on fair classifiers has drawn significant attention to develop effective algorithms to achieve fairness and good classification performance. Despite the great success of these fairness-aware machine learning models, most of the existing models require sensitive attributes to preprocess the data, regularize the model learning or postprocess the prediction to have fair predictions. However, sensitive attributes are often incomplete or even unavailable due to privacy, legal or regulation restrictions. Though we lack the sensitive attribute for training a fair model in the target domain, there might exist a similar domain that has sensitive attributes. Thus, it is important to exploit auxiliary information from the similar domain to help improve fair classification in the target domain. Therefore, in this paper, we study a novel problem of exploring domain adaptation for fair classification. We propose a new framework that can simultaneously estimate the sensitive attributes while learning a fair classifier in the target domain. Extensive experiments on real-world datasets illustrate the effectiveness of the proposed model for fair classification, even when no sensitive attributes are available in the target domain.

FINETUNA: Fine-tuning Accelerated Molecular Simulations

Machine learning approaches have the potential to approximate Density Functional Theory (DFT) for atomistic simulations in a computationally efficient manner, which could dramatically increase the impact of computational simulations on real-world problems. However, they are limited by their accuracy and the cost of generating labeled data. Here, we present an online active learning framework for accelerating the simulation of atomic systems efficiently and accurately by incorporating prior physical information learned by large-scale pre-trained graph neural network models from the Open Catalyst Project. Accelerating these simulations enables useful data to be generated more cheaply, allowing better models to be trained and more atomistic systems to be screened. We also present a method of comparing local optimization techniques on the basis of both their speed and accuracy. Experiments on 30 benchmark adsorbate-catalyst systems show that our method of transfer learning to incorporate prior information from pre-trained models accelerates simulations by reducing the number of DFT calculations by 91%, while meeting an accuracy threshold of 0.02 eV 93% of the time. Finally, we demonstrate a technique for leveraging the interactive functionality built in to VASP to efficiently compute single point calculations within our online active learning framework without the significant startup costs. This allows VASP to work in tandem with our framework while requiring 75% fewer self-consistent cycles than conventional single point calculations. The online active learning implementation, and examples using the VASP interactive code, are available in the open source FINETUNA package on Github.

What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks?

Self-supervised learning establishes a new paradigm of learning representations with much fewer or even no label annotations. Recently there has been remarkable progress on large-scale contrastive learning models which require substantial computing resources, yet such models are not practically optimal for small-scale tasks. To fill the gap, we aim to study contrastive learning on the wearable-based activity recognition task. Specifically, we conduct an in-depth study of contrastive learning from both algorithmic-level and task-level perspectives. For algorithmic-level analysis, we decompose contrastive models into several key components and conduct rigorous experimental evaluations to better understand the efficacy and rationale behind contrastive learning. More importantly, for task-level analysis, we show that the wearable-based signals bring unique challenges and opportunities to existing contrastive models, which cannot be readily solved by existing algorithms. Our thorough empirical studies suggest important practices and shed light on future research challenges. In the meantime, this paper presents an open-source PyTorch library \texttt{CL-HAR}, which can serve as a practical tool for researchers. The library is highly modularized and easy to use, which opens up avenues for exploring novel contrastive models quickly in the future.

Dynamic Window-level Granger Causality of Multi-channel Time Series

Granger causality method analyzes the time series causalities without building a complex causality graph. However, the traditional Granger causality method assumes that the causalities lie between time series channels and remain constant, which cannot model the real-world time series data with dynamic causalities along the time series channels. In this paper, we present the dynamic window-level Granger causality method (DWGC) for multi-channel time series data. We build the causality model on the window-level by doing the F-test with the forecasting errors on the sliding windows. We propose the causality indexing trick in our DWGC method to reweight the original time series data. Essentially, the causality indexing is to decrease the auto-correlation and increase the cross-correlation causal effects, which improves the DWGC method. Theoretical analysis and experimental results on two synthetic and one real-world datasets show that the improved DWGC method with causality indexing better detects the window-level causalities.

VFlow: More Expressive Generative Flows with Variational Data Augmentation

Generative flows are promising tractable models for density modeling that define probabilistic distributions with invertible transformations. However, tractability imposes architectural constraints on generative flows, making them less expressive than other types of generative models. In this work, we study a previously overlooked constraint that all the intermediate representations must have the same dimensionality with the original data due to invertibility, limiting the width of the network. We tackle this constraint by augmenting the data with some extra dimensions and jointly learning a generative flow for augmented data as well as the distribution of augmented dimensions under a variational inference framework. Our approach, VFlow, is a generalization of generative flows and therefore always performs better. Combining with existing generative flows, VFlow achieves a new state-of-the-art 2.98 bits per dimension on the CIFAR-10 dataset and is more compact than previous models to reach similar modeling quality.

MinAtar: An Atari-inspired Testbed for More Efficient Reinforcement Learning Experiments

The Arcade Learning Environment (ALE) is a popular platform for evaluating reinforcement learning agents. Much of the appeal comes from the fact that Atari games are varied, showcase aspects of competency we expect from an intelligent agent, and are not biased towards any particular solution approach. The challenge of the ALE includes 1) the representation learning problem of extracting pertinent information from the raw pixels, and 2) the behavioural learning problem of leveraging complex, delayed associations between actions and rewards. Often, in reinforcement learning research, we care more about the latter, but the representation learning problem adds significant computational expense. In response, we introduce MinAtar, short for miniature Atari, a new evaluation platform that captures the general mechanics of specific Atari games, while simplifying certain aspects. In particular, we reduce the representational complexity to focus more on behavioural challenges. MinAtar consists of analogues to five Atari games which play out on a 10x10 grid. MinAtar provides a 10x10xn state representation. The n channels correspond to game-specific objects, such as ball, paddle and brick in the game Breakout. While significantly simplified, these domains are still rich enough to allow for interesting behaviours. To demonstrate the challenges posed by these domains, we evaluated a smaller version of the DQN architecture. We also tried variants of DQN without experience replay, and without a target network, to assess the impact of those two prominent components in the MinAtar environments. In addition, we evaluated a simpler agent that used actor-critic with eligibility traces, online updating, and no experience replay. We hope that by introducing a set of simplified, Atari-like games we can allow researchers to more efficiently investigate the unique behavioural challenges provided by the ALE.