arXiv subjects

Zhihua Zhang

Publications and source records attributed to Zhihua Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Enhancing Diagnostic Precision in Gastric Bleeding through Automated Lesion Segmentation: A Deep DuS-KFCM Approach

Timely and precise classification and segmentation of gastric bleeding in endoscopic imagery are pivotal for the rapid diagnosis and intervention of gastric complications, which is critical in life-saving medical procedures. Traditional methods grapple with the challenge posed by the indistinguishable intensity values of bleeding tissues adjacent to other gastric structures. Our study seeks to revolutionize this domain by introducing a novel deep learning model, the Dual Spatial Kernelized Constrained Fuzzy C-Means (Deep DuS-KFCM) clustering algorithm. This Hybrid Neuro-Fuzzy system synergizes Neural Networks with Fuzzy Logic to offer a highly precise and efficient identification of bleeding regions. Implementing a two-fold coarse-to-fine strategy for segmentation, this model initially employs the Spatial Kernelized Fuzzy C-Means (SKFCM) algorithm enhanced with spatial intensity profiles and subsequently harnesses the state-of-the-art DeepLabv3+ with ResNet50 architecture to refine the segmentation output. Through extensive experiments across mainstream gastric bleeding and red spots datasets, our Deep DuS-KFCM model demonstrated unprecedented accuracy rates of 87.95%, coupled with a specificity of 96.33%, outperforming contemporary segmentation methods. The findings underscore the model's robustness against noise and its outstanding segmentation capabilities, particularly for identifying subtle bleeding symptoms, thereby presenting a significant leap forward in medical image processing.

eess.IV↗

arXiv2024

Principal-Agent Problem with Third Party: Information Design from Social Planner's Perspective

We study the principal-agent problem with a third party that we call social planner, whose responsibility is to reconcile the conflicts of interest between the two players and induce socially optimal outcome in terms of some given social utility function. The social planner owns no contractual power but manages to control the information flow between the principal and the agent. We design a simple workflow with two stages for the social planner. In the first stage, the problem is reformulated as an optimization problem whose solution is the optimal utility profile. In the second stage, we investigate information design and show that binary-signal information structure suffices to induce the socially optimal outcome determined in the first stage. The simplicity and modularity of our method make it easy to implement in various scenarios within the principal-agent problem.

cs.GT↗

arXiv2024

Asymptotic Time-Uniform Inference for Parameters in Averaged Stochastic Approximation

We study time-uniform statistical inference for parameters in stochastic approximation (SA), which encompasses a bunch of applications in optimization and machine learning. To that end, we analyze the almost-sure convergence rates of the averaged iterates to a scaled sum of Gaussians in both linear and nonlinear SA problems. We then construct three types of asymptotic confidence sequences that are valid uniformly across all times with coverage guarantees, in an asymptotic sense that the starting time is sufficiently large. These coverage guarantees remain valid if the unknown covariance matrix is replaced by its plug-in estimator, and we conduct experiments to validate our methodology.

stat.ML↗

arXiv2024

Estimation and Inference in Distributional Reinforcement Learning

In this paper, we study distributional reinforcement learning from the perspective of statistical efficiency. We investigate distributional policy evaluation, aiming to estimate the complete return distribution (denoted $η^π$) attained by a given policy $π$. We use the certainty-equivalence method to construct our estimator $\hatη^π$, given a generative model is available. In this circumstance we need a dataset of size $\widetilde O\left(\frac{|\mathcal{S}||\mathcal{A}|}{\varepsilon^{2p}(1-γ)^{2p+2}}\right)$ to guarantee the $p$-Wasserstein metric between $\hatη^π$ and $η^π$ less than $\varepsilon$ with high probability. This implies the distributional policy evaluation problem can be solved with sample efficiency. Also, we show that under different mild assumptions a dataset of size $\widetilde O\left(\frac{|\mathcal{S}||\mathcal{A}|}{\varepsilon^{2}(1-γ)^{4}}\right)$ suffices to ensure the Kolmogorov metric and total variation metric between $\hatη^π$ and $η^π$ is below $\varepsilon$ with high probability. Furthermore, we investigate the asymptotic behavior of $\hatη^π$. We demonstrate that the ``empirical process'' $\sqrt{n}(\hatη^π-η^π)$ converges weakly to a Gaussian process in the space of bounded functionals on Lipschitz function class $\ell^\infty(\mathcal{F}_{\text{W}})$, also in the space of bounded functionals on indicator function class $\ell^\infty(\mathcal{F}_{\text{KS}})$ and bounded measurable function class $\ell^\infty(\mathcal{F}_{\text{TV}})$ when some mild conditions hold. Our findings give rise to a unified approach to statistical inference of a wide class of statistical functionals of $η^π$.

stat.ML↗

arXiv2024

On the Convergence of Projected Policy Gradient for Any Constant Step Sizes

Projected policy gradient (PPG) is a basic policy optimization method in reinforcement learning. Given access to exact policy evaluations, previous studies have established the sublinear convergence of PPG for sufficiently small step sizes based on the smoothness and the gradient domination properties of the value function. However, as the step size goes to infinity, PPG reduces to the classic policy iteration method, which suggests the convergence of PPG even for large step sizes. In this paper, we fill this gap and show that PPG admits a sublinear convergence for any constant step sizes. Due to the existence of the state-wise visitation measure in the expression of policy gradient, the existing optimization-based analysis framework for a preconditioned version of PPG (i.e., projected Q-ascent) is not applicable, to the best of our knowledge. Instead, we proceed the proof by computing the state-wise improvement lower bound of PPG based on its inherent structure. In addition, the finite iteration convergence of PPG for any constant step size is further established, which is also new.

math.OC↗

arXiv2024

On the Convergence of Policy in Unregularized Policy Mirror Descent

In this short note, we give the convergence analysis of the policy in the recent famous policy mirror descent (PMD). We mainly consider the unregularized setting following [11] with generalized Bregman divergence. The difference is that we directly give the convergence rates of policy under generalized Bregman divergence. Our results are inspired by the convergence of value function in previous works and are an extension study of policy mirror descent. Though some results have already appeared in previous work, we further discover a large body of Bregman divergences could give finite-step convergence to an optimal policy, such as the classical Euclidean distance.

math.OC↗

arXiv2024

Federated Control in Markov Decision Processes

We study problems of federated control in Markov Decision Processes. To solve an MDP with large state space, multiple learning agents are introduced to collaboratively learn its optimal policy without communication of locally collected experience. In our settings, these agents have limited capabilities, which means they are restricted within different regions of the overall state space during the training process. In face of the difference among restricted regions, we firstly introduce concepts of leakage probabilities to understand how such heterogeneity affects the learning process, and then propose a novel communication protocol that we call Federated-Q protocol (FedQ), which periodically aggregates agents' knowledge of their restricted regions and accordingly modifies their learning problems for further training. In terms of theoretical analysis, we justify the correctness of FedQ as a communication protocol, then give a general result on sample complexity of derived algorithms FedQ-X with the RL oracle , and finally conduct a thorough study on the sample complexity of FedQ-SynQ. Specifically, FedQ-X has been shown to enjoy linear speedup in terms of sample complexity when workload is uniformly distributed among agents. Moreover, we carry out experiments in various environments to justify the efficiency of our methods.

stat.ML↗

arXiv2024

Federated Reinforcement Learning with Constraint Heterogeneity

We study a Federated Reinforcement Learning (FedRL) problem with constraint heterogeneity. In our setting, we aim to solve a reinforcement learning problem with multiple constraints while $N$ training agents are located in $N$ different environments with limited access to the constraint signals and they are expected to collaboratively learn a policy satisfying all constraint signals. Such learning problems are prevalent in scenarios of Large Language Model (LLM) fine-tuning and healthcare applications. To solve the problem, we propose federated primal-dual policy optimization methods based on traditional policy gradient methods. Specifically, we introduce $N$ local Lagrange functions for agents to perform local policy updates, and these agents are then scheduled to periodically communicate on their local policies. Taking natural policy gradient (NPG) and proximal policy optimization (PPO) as policy optimization methods, we mainly focus on two instances of our algorithms, ie, {FedNPG} and {FedPPO}. We show that FedNPG achieves global convergence with an $\tilde{O}(1/\sqrt{T})$ rate, and FedPPO efficiently solves complicated learning tasks with the use of deep neural networks.

cs.LG↗

arXiv2024

Anderson Acceleration Without Restart: A Novel Method with $n$-Step Super Quadratic Convergence Rate

In this paper, we propose a novel Anderson's acceleration method to solve nonlinear equations, which does \emph{not} require a restart strategy to achieve numerical stability. We propose the greedy and random versions of our algorithm. Specifically, the greedy version selects the direction to maximize a certain measure of progress for approximating the current Jacobian matrix. In contrast, the random version chooses the random Gaussian vector as the direction to update the approximate Jacobian. Furthermore, our algorithm, including both greedy and random versions, has an $n$-step super quadratic convergence rate, where $n$ is the dimension of the objective problem. For example, the explicit convergence rate of the random version can be presented as $ \norm{\vx_{k+n+1} - \vx_*} / \norm{\vx_k- \vx_*}^2 = \cO\left(\left(1-\frac{1}{n}\right)^{kn}\right)$ for any $k\geq 0$ where $\vx_*$ is the optimum of the objective problem. This kind of convergence rate is new to Anderson's acceleration and quasi-Newton methods. The experiments also validate the fast convergence rate of our algorithm.

math.OC↗

arXiv2024

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models

Due to the ease of training, ability to scale, and high sample quality, diffusion models (DMs) have become the preferred option for generative modeling, with numerous pre-trained models available for a wide variety of datasets. Containing intricate information about data distributions, pre-trained DMs are valuable assets for downstream applications. In this work, we consider learning from pre-trained DMs and transferring their knowledge to other generative models in a data-free fashion. Specifically, we propose a general framework called Diff-Instruct to instruct the training of arbitrary generative models as long as the generated samples are differentiable with respect to the model parameters. Our proposed Diff-Instruct is built on a rigorous mathematical foundation where the instruction process directly corresponds to minimizing a novel divergence we call Integral Kullback-Leibler (IKL) divergence. IKL is tailored for DMs by calculating the integral of the KL divergence along a diffusion process, which we show to be more robust in comparing distributions with misaligned supports. We also reveal non-trivial connections of our method to existing works such as DreamFusion, and generative adversarial training. To demonstrate the effectiveness and universality of Diff-Instruct, we consider two scenarios: distilling pre-trained diffusion models and refining existing GAN models. The experiments on distilling pre-trained diffusion models show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. The experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models across various settings.

cs.LG↗

arXiv2023

Gradient Tracking for High Dimensional Federated Optimization

In this paper, we study the (decentralized) distributed optimization problem with high-dimensional sparse structure. Building upon the FedDA algorithm, we propose a (Decentralized) FedDA-GT algorithm, which combines the \textbf{gradient tracking} technique. It is able to eliminate the heterogeneity among different clients' objective functions while ensuring a dimension-free convergence rate. Compared to the vanilla FedDA approach, (D)FedDA-GT can significantly reduce the communication complexity, from ${O}(s^2\log d/\varepsilon^{3/2})$ to a more efficient ${O}(s^2\log d/\varepsilon)$. In cases where strong convexity is applicable, we introduce a multistep mechanism resulting in the Multistep ReFedDA-GT algorithm, a minor modified version of FedDA-GT. This approach achieves an impressive communication complexity of ${O}\left(s\log d \log \frac{1}{\varepsilon}\right)$ through repeated calls to the ReFedDA-GT algorithm. Finally, we conduct numerical experiments, illustrating that our proposed algorithms enjoy the dual advantage of being dimension-free and heterogeneity-free.

math.OC↗

arXiv2023

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

We study finite-sum distributed optimization problems involving a master node and $n-1$ local nodes under the popular $δ$-similarity and $μ$-strong convexity conditions. We propose two new algorithms, SVRS and AccSVRS, motivated by previous works. The non-accelerated SVRS method combines the techniques of gradient sliding and variance reduction and achieves a better communication complexity of $\tilde{\mathcal{O}}(n {+} \sqrt{n}δ/μ)$ compared to existing non-accelerated algorithms. Applying the framework proposed in Katyusha X, we also develop a directly accelerated version named AccSVRS with the $\tilde{\mathcal{O}}(n {+} n^{3/4}\sqrt{δ/μ})$ communication complexity. In contrast to existing results, our complexity bounds are entirely smoothness-free and exhibit superiority in ill-conditioned cases. Furthermore, we establish a nearly matched lower bound to verify the tightness of our AccSVRS method.

cs.LG↗

arXiv2023

Enhancing Adversarial Robustness via Score-Based Optimization

Adversarial attacks have the potential to mislead deep neural network classifiers by introducing slight perturbations. Developing algorithms that can mitigate the effects of these attacks is crucial for ensuring the safe use of artificial intelligence. Recent studies have suggested that score-based diffusion models are effective in adversarial defenses. However, existing diffusion-based defenses rely on the sequential simulation of the reversed stochastic differential equations of diffusion models, which are computationally inefficient and yield suboptimal results. In this paper, we introduce a novel adversarial defense scheme named ScoreOpt, which optimizes adversarial samples at test-time, towards original clean data in the direction guided by score-based priors. We conduct comprehensive experiments on multiple datasets, including CIFAR10, CIFAR100 and ImageNet. Our experimental results demonstrate that our approach outperforms existing adversarial defenses in terms of both robustness performance and inference speed.

cs.LG↗

arXiv2023

Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness

Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suitable pre-processing. Diffusion models have been shown to be effective for adversarial purification. Despite their success, many aspects of diffusion purification still remain unexplored. In this paper, we investigate and improve upon three limiting designs of diffusion purification: the use of an improved diffusion model, advanced numerical simulation techniques, and optimal control of randomness. Based on our findings, we propose Purify++, a new diffusion purification algorithm that is now the state-of-the-art purification method against several adversarial attacks. Our work presents a systematic exploration of the limits of diffusion purification methods.

cs.LG↗

arXiv2023

Constructing Synthetic Treatment Groups without the Mean Exchangeability Assumption

The purpose of this work is to transport the information from multiple randomized controlled trials to the target population where we only have the control group data. Previous works rely critically on the mean exchangeability assumption. However, as pointed out by many current studies, the mean exchangeability assumption might be violated. Motivated by the synthetic control method, we construct a synthetic treatment group for the target population by a weighted mixture of treatment groups of source populations. We estimate the weights by minimizing the conditional maximum mean discrepancy between the weighted control groups of source populations and the target population. We establish the asymptotic normality of the synthetic treatment group estimator based on the sieve semiparametric theory. Our method can serve as a novel complementary approach when the mean exchangeability assumption is violated. Experiments are conducted on synthetic and real-world datasets to demonstrate the effectiveness of our methods.

stat.ML↗

arXiv2023

Robust Markov Decision Processes without Model Estimation

Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However, there are two major barriers to applying robust MDPs in practice. First, most works study robust MDPs in a model-based regime, where the transition probability needs to be estimated and requires a large amount of memories $\mathcal{O}(|\mathcal{S}|^2|\mathcal{A}|)$. Second, prior work typically assumes a strong oracle to obtain the optimal solution as an intermediate step to solve robust MDPs. However, in practice, such an oracle does not exist usually. To remove the oracle, we transform the original robust MDPs into an alternative form, which allows us to use stochastic gradient methods to solve the robust MDPs. Moreover, we prove the alternative form still plays a similar role as the original form. With this new formulation, we devise a sample-efficient algorithm to solve the robust MDPs in a model-free regime, which does not require an oracle and trades off a lower storage requirement $\mathcal{O}(|\mathcal{S}||\mathcal{A}|)$ with being able to generate samples from a generative model or Markovian chain. Finally, we validate our theoretical findings via numerical experiments, showing the efficiency with the alternative form of robust MDPs.

stat.ML↗

arXiv2023

Near-Optimal Last-iterate Convergence of Policy Optimization in Zero-sum Polymatrix Markov games

Computing approximate Nash equilibria in multi-player general-sum Markov games is a computationally intractable task. However, multi-player Markov games with certain cooperative or competitive structures might circumvent this intractability. In this paper, we focus on multi-player zero-sum polymatrix Markov games, where players interact in a pairwise fashion while remain overall competitive. To the best of our knowledge, we propose the first policy optimization algorithm called Entropy-Regularized Optimistic-Multiplicative-Weights-Update (ER-OMWU) for finding approximate Nash equilibria in finite-horizon zero-sum polymatrix Markov games with full information feedback. We provide last-iterate convergence guarantees for finding an $ε$-approximate Nash equilibrium within $\tilde{O}(1/ε)$ iterations, which is near-optimal compared to the optimal $O(1/ε)$ iteration complexity in two-player zero-sum Markov games, which is a degenerate case of zero-sum polymatrix games with only two players involved. Our algorithm combines the regularized and optimistic learning dynamics with separated smooth value update within a single loop, where players update strategies in a symmetric and almost uncoupled manner. It provides a natural dynamics for finding equilibria and is more probable to be adapted to a sample-efficient and fully decentralized implementation where only partial information feedback is available in the future.

cs.GT↗

arXiv2023

Training Energy-Based Models with Diffusion Contrastive Divergences

Energy-Based Models (EBMs) have been widely used for generative modeling. Contrastive Divergence (CD), a prevailing training objective for EBMs, requires sampling from the EBM with Markov Chain Monte Carlo methods (MCMCs), which leads to an irreconcilable trade-off between the computational burden and the validity of the CD. Running MCMCs till convergence is computationally intensive. On the other hand, short-run MCMC brings in an extra non-negligible parameter gradient term that is difficult to handle. In this paper, we provide a general interpretation of CD, viewing it as a special instance of our proposed Diffusion Contrastive Divergence (DCD) family. By replacing the Langevin dynamic used in CD with other EBM-parameter-free diffusion processes, we propose a more efficient divergence. We show that the proposed DCDs are both more computationally efficient than the CD and are not limited to a non-negligible gradient term. We conduct intensive experiments, including both synthesis data modeling and high-dimensional image denoising and generation, to show the advantages of the proposed DCDs. On the synthetic data learning and image denoising experiments, our proposed DCD outperforms CD by a large margin. In image generation experiments, the proposed DCD is capable of training an energy-based model for generating the Celab-A $32\times 32$ dataset, which is comparable to existing EBMs.

cs.LG↗