Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learning

This study presents an unsupervised domain adaptation method aimed at autonomously generating image masks outlining regions of interest (ROIs) for differentiating breast lesions in breast ultrasound (US) imaging. Our semi-supervised learning approach utilizes a primitive model trained on a small public breast US dataset with true annotations. This model is then iteratively refined for the domain adaptation task, generating pseudo-masks for our private, unannotated breast US dataset. The dataset, twice the size of the public one, exhibits considerable variability in image acquisition perspectives and demographic representation, posing a domain-shift challenge. Unlike typical domain adversarial training, we employ downstream classification outcomes as a benchmark to guide the updating of pseudo-masks in subsequent iterations. We found the classification precision to be highly correlated with the completeness of the generated ROIs, which promotes the explainability of the deep learning classification model. Preliminary findings demonstrate the efficacy and reliability of this approach in streamlining the ROI annotation process, thereby enhancing the classification and localization of breast lesions for more precise and interpretable diagnoses.

Entrywise Inference for Causal Panel Data: A Simple and Instance-Optimal Approach

In causal inference with panel data under staggered adoption, the goal is to estimate and derive confidence intervals for potential outcomes and treatment effects. We propose a computationally efficient procedure, involving only simple matrix algebra and singular value decomposition. We derive non-asymptotic bounds on the entrywise error, establishing its proximity to a suitably scaled Gaussian variable. Despite its simplicity, our procedure turns out to be instance-optimal, in that our theoretical scaling matches a local instance-wise lower bound derived via a Bayesian Cram\'{e}r-Rao argument. Using our insights, we develop a data-driven procedure for constructing entrywise confidence intervals with pre-specified coverage guarantees. Our analysis is based on a general inferential toolbox for the SVD algorithm applied to the matrix denoising model, which might be of independent interest.

The Isotonic Mechanism for Exponential Family Estimation

In 2023, the International Conference on Machine Learning (ICML) required authors with multiple submissions to rank their submissions based on perceived quality. In this paper, we aim to employ these author-specified rankings to enhance peer review in machine learning and artificial intelligence conferences by extending the Isotonic Mechanism (Su, 2021, 2022) to exponential family distributions. This mechanism generates adjusted scores closely align with the original scores while adhering to author-specified rankings. Despite its applicability to a broad spectrum of exponential family distributions, this mechanism's implementation does not necessitate knowledge of the specific distribution form. We demonstrate that an author is incentivized to provide accurate rankings when her utility takes the form of a convex additive function of the adjusted review scores. For a certain subclass of exponential family distributions, we prove that the author reports truthfully only if the question involves only pairwise comparisons between her submissions, thus indicating the optimality of ranking in truthful information elicitation. Lastly, we show that the adjusted scores improve dramatically the accuracy of the original scores and achieve nearly minimax optimality for estimating the true scores with statistical consistecy when true scores have bounded total variation.

Minimax-Optimal Reward-Agnostic Exploration in Reinforcement Learning

This paper studies reward-agnostic exploration in reinforcement learning (RL) -- a scenario where the learner is unware of the reward functions during the exploration stage -- and designs an algorithm that improves over the state of the art. More precisely, consider a finite-horizon non-stationary Markov decision process with $S$ states, $A$ actions, and horizon length $H$, and suppose that there are no more than a polynomial number of given reward functions of interest. By collecting an order of \begin{align*} \frac{SAH^3}{\varepsilon^2} \text{ sample episodes (up to log factor)} \end{align*} without guidance of the reward information, our algorithm is able to find $\varepsilon$-optimal policies for all these reward functions, provided that $\varepsilon$ is sufficiently small. This forms the first reward-agnostic exploration scheme in this context that achieves provable minimax optimality. Furthermore, once the sample size exceeds $\frac{S^2AH^3}{\varepsilon^2}$ episodes (up to log factor), our algorithm is able to yield $\varepsilon$ accuracy for arbitrarily many reward functions (even when they are adversarially designed), a task commonly dubbed as ``reward-free exploration.'' The novelty of our algorithm design draws on insights from offline RL: the exploration scheme attempts to maximize a critical reward-agnostic quantity that dictates the performance of offline RL, while the policy learning paradigm leverages ideas from sample-optimal offline RL paradigms.

Learning Gaussian Mixtures Using the Wasserstein-Fisher-Rao Gradient Flow

Gaussian mixture models form a flexible and expressive parametric family of distributions that has found applications in a wide variety of applications. Unfortunately, fitting these models to data is a notoriously hard problem from a computational perspective. Currently, only moment-based methods enjoy theoretical guarantees while likelihood-based methods are dominated by heuristics such as Expectation-Maximization that are known to fail in simple examples. In this work, we propose a new algorithm to compute the nonparametric maximum likelihood estimator (NPMLE) in a Gaussian mixture model. Our method is based on gradient descent over the space of probability measures equipped with the Wasserstein-Fisher-Rao geometry for which we establish convergence guarantees. In practice, it can be approximated using an interacting particle system where the weight and location of particles are updated alternately. We conduct extensive numerical experiments to confirm the effectiveness of the proposed algorithm compared not only to classical benchmarks but also to similar gradient descent algorithms with respect to simpler geometries. In particular, these simulations illustrate the benefit of updating both weight and location of the interacting particles.

Model-Based Reinforcement Learning Is Minimax-Optimal for Offline Zero-Sum Markov Games

This paper makes progress towards learning Nash equilibria in two-player zero-sum Markov games from offline data. Specifically, consider a $\gamma$-discounted infinite-horizon Markov game with $S$ states, where the max-player has $A$ actions and the min-player has $B$ actions. We propose a pessimistic model-based algorithm with Bernstein-style lower confidence bounds -- called VI-LCB-Game -- that provably finds an $\varepsilon$-approximate Nash equilibrium with a sample complexity no larger than $\frac{C_{\mathsf{clipped}}^{\star}S(A+B)}{(1-\gamma)^{3}\varepsilon^{2}}$ (up to some log factor). Here, $C_{\mathsf{clipped}}^{\star}$ is some unilateral clipped concentrability coefficient that reflects the coverage and distribution shift of the available data (vis-\`a-vis the target data), and the target accuracy $\varepsilon$ can be any value within $\big(0,\frac{1}{1-\gamma}\big]$. Our sample complexity bound strengthens prior art by a factor of $\min\{A,B\}$, achieving minimax optimality for the entire $\varepsilon$-range. An appealing feature of our result lies in algorithmic simplicity, which reveals the unnecessity of variance reduction and sample splitting in achieving sample optimality.

The Efficacy of Pessimism in Asynchronous Q-Learning

This paper is concerned with the asynchronous form of Q-learning, which applies a stochastic approximation scheme to Markovian data samples. Motivated by the recent advances in offline reinforcement learning, we develop an algorithmic framework that incorporates the principle of pessimism into asynchronous Q-learning, which penalizes infrequently-visited state-action pairs based on suitable lower confidence bounds (LCBs). This framework leads to, among other things, improved sample efficiency and enhanced adaptivity in the presence of near-expert data. Our approach permits the observed data in some important scenarios to cover only partial state-action space, which is in stark contrast to prior theory that requires uniform coverage of all state-action pairs. When coupled with the idea of variance reduction, asynchronous Q-learning with LCB penalization achieves near-optimal sample complexity, provided that the target accuracy level is small enough. In comparison, prior works were suboptimal in terms of the dependency on the effective horizon even when i.i.d. sampling is permitted. Our results deliver the first theoretical support for the use of pessimism principle in the presence of Markovian non-i.i.d. data.

Inference for Heteroskedastic PCA with Missing Data

This paper studies how to construct confidence regions for principal component analysis (PCA) in high dimension, a problem that has been vastly under-explored. While computing measures of uncertainty for nonlinear/nonconvex estimators is in general difficult in high dimension, the challenge is further compounded by the prevalent presence of missing data and heteroskedastic noise. We propose a suite of solutions to perform valid inference on the principal subspace based on two estimators: a vanilla SVD-based approach, and a more refined iterative scheme called $\textsf{HeteroPCA}$ (Zhang et al., 2018). We develop non-asymptotic distributional guarantees for both estimators, and demonstrate how these can be invoked to compute both confidence regions for the principal subspace and entrywise confidence intervals for the spiked covariance matrix. Particularly worth highlighting is the inference procedure built on top of $\textsf{HeteroPCA}$, which is not only valid but also statistically efficient for broader scenarios (e.g., it covers a wider range of missing rates and signal-to-noise ratios). Our solutions are fully data-driven and adaptive to heteroskedastic random noise, without requiring prior knowledge about the noise levels and noise distributions.

Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model

The curse of dimensionality is a widely known issue in reinforcement learning (RL). In the tabular setting where the state space $\mathcal{S}$ and the action space $\mathcal{A}$ are both finite, to obtain a nearly optimal policy with sampling access to a generative model, the minimax optimal sample complexity scales linearly with $|\mathcal{S}|\times|\mathcal{A}|$, which can be prohibitively large when $\mathcal{S}$ or $\mathcal{A}$ is large. This paper considers a Markov decision process (MDP) that admits a set of state-action features, which can linearly express (or approximate) its probability transition kernel. We show that a model-based approach (resp.$~$Q-learning) provably learns an $\varepsilon$-optimal policy (resp.$~$Q-function) with high probability as soon as the sample size exceeds the order of $\frac{K}{(1-\gamma)^{3}\varepsilon^{2}}$ (resp.$~$$\frac{K}{(1-\gamma)^{4}\varepsilon^{2}}$), up to some logarithmic factor. Here $K$ is the feature dimension and $\gamma\in(0,1)$ is the discount factor of the MDP. Both sample complexity bounds are provably tight, and our result for the model-based approach matches the minimax lower bound. Our results show that for arbitrarily large-scale MDP, both the model-based approach and Q-learning are sample-efficient when $K$ is relatively small, and hence the title of this paper.