研究园简易版 · 经典书籍 · 期刊文章 · 有原文 · 完整版(可多选筛选、搜索) · 首页
2025 年 · Optimization & Learning Theory(优化与学习理论)
105 篇,新的在前。点标题看作者和摘要。回到 2025 年
- A New Approach to Optimal Design under Model Uncertainty Motivated by Multi-Armed Bandits · JASA · 2025-12-22 · 在第 1 页
- SMART-MC: Characterizing the Dynamics of Multiple Sclerosis Therapy Transitions Using a Covariate-Based Markov Model · JASA · 2025-12-08 · 在第 2 页
- Geodesic optimal transport regression · Biometrika · 2025-12-02 · 在第 3 页
- Optimal sequencing depth for single-cell RNA-sequencing in Wasserstein space · AoS · 2025-12-01 · 在第 3 页
- Online Policy Learning and Inference by Matrix Completion · JASA · 2025-10-10 · 在第 6 页
- Randomized optimal selection design for dose optimization · Biometrics · 2025-10-08 · 在第 6 页
- Estimation of Out-of-Sample Sharpe Ratio for High Dimensional Portfolio Optimization · JASA · 2025-09-30 · 在第 8 页
- Optimal Transport based Cross-Domain Integration for Heterogeneous Data · JASA · 2025-09-17 · 在第 8 页
- A robust Bayesian dose optimization design with backfill and randomization for phase I/II clinical trials · SMMR · 2025-09-05 · 在第 9 页
- Wasserstein generative regression · JRSSB · 2025-08-25 · 在第 10 页
- Distributional Off-Policy Evaluation in Reinforcement Learning · JASA · 2025-08-05 · 在第 11 页
- Reinforcement learning for individual optimal policy from heterogeneous data · AoS · 2025-08-01 · 在第 12 页
- Entrywise dynamics and universality of general first order methods · AoS · 2025-08-01 · 在第 12 页
- Precision generalized phase I-II designs · Biometrics · 2025-07-24 · 在第 12 页
- COCA: a randomized Bayesian design integrating dose optimization and component contribution assessment for combination therapies · Biometrics · 2025-06-24 · 在第 15 页
- Design optimization of longitudinal studies using metaheuristics: Application to lithium pharmacokinetics · SMMR · 2025-06-19 · 在第 16 页
- Optimal transport map estimation in general function spaces · AoS · 2025-06-01 · 在第 17 页
- Estimating optimally tailored active surveillance strategy under interval censoring · Biometrics · 2025-05-30 · 在第 17 页
- UNITED: A Unified Transparent and Efficient Phase I/II Trial Design for Dose Optimization Accounting for Ordinal Graded, Continuous and Mixed Toxicity and Efficacy Endpoints · SiM · 2025-05-19 · 在第 19 页
- TODO: A Triple‐Outcome Double‐Criterion Optimal Design for Dose Monitoring‐and‐Optimization in Multi‐Dose Randomized Trials · SiM · 2025-05-19 · 在第 19 页
- Sample Size Calculation in Dose Optimization Trials Using the Margin of Practical Non‐Inferiority · SiM · 2025-05-19 · 在第 19 页
- COMIC: A Bayesian Dose Optimization Design for Drug Combination in Multiple Indications With Application to CAR‐T Therapies · SiM · 2025-05-19 · 在第 19 页
- A model-free phase I/II dose optimization design for immunotherapy trials · SMMR · 2025-05-15 · 在第 19 页
- A Generalized Phase I/II Dose Optimization Trial Design With Multi‐Categorical and Multi‐Graded Outcomes · SiM · 2025-04-11 · 在第 21 页
- The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime · AoS · 2025-04-01 · 在第 22 页
- Large-dimensional independent component analysis: Statistical optimality and computational tractability · AoS · 2025-04-01 · 在第 22 页
- DOD ‐ SSR : An Adaptive Seamless Phase II / III Design With Dose Optimization Decision and Sample Size Re‐estimation · SiM · 2025-02-07 · 在第 26 页
- Unified algorithms for RL with Decision-Estimation Coefficients: PAC, reward-free, preference-based learning and beyond · AoS · 2025-02-01 · 在第 26 页
- On the sample complexity of entropic optimal transport · AoS · 2025-02-01 · 在第 26 页
- Computationally efficient and statistically optimal robust high-dimensional linear regression · AoS · 2025-02-01 · 在第 27 页
- When Composite Likelihood meets Stochastic Approximation · JASA · 2025-01-31 · 在第 27 页
- Optimal Multitask Linear Regression and Contextual Bandits under Sparse Heterogeneity · JASA · 2025-01-31 · 在第 27 页
- Weighted Q-learning for optimal dynamic treatment regimes with nonignorable missing covariates · Biometrics · 2025-01-07 · 在第 28 页
- Wasserstein F-tests for Frechet regression on Bures-Wasserstein manifolds · JMLR · 2025 · 在第 29 页
- Wasserstein Convergence Guarantees for a General Class of Score-Based Generative Models · JMLR · 2025 · 在第 29 页
- Universal Online Convex Optimization Meets Second-order Bounds · JMLR · 2025 · 在第 29 页
- Two-Timescale Gradient Descent Ascent Algorithms for Nonconvex Minimax Optimization · JMLR · 2025 · 在第 29 页
- The Z-Gromov-Wasserstein Distance · JMLR · 2025 · 在第 29 页
- The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning · JMLR · 2025 · 在第 29 页
- The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond · JMLR · 2025 · 在第 29 页
- Stochastic Interior-Point Methods for Smooth Conic Optimization with Applications · JMLR · 2025 · 在第 30 页
- Statistical field theory for Markov decision processes under uncertainty · JMLR · 2025 · 在第 30 页
- Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming · JMLR · 2025 · 在第 30 页
- Sliced-Wasserstein Distances and Flows on Cartan-Hadamard Manifolds · JMLR · 2025 · 在第 30 页
- Simplex Constrained Sparse Optimization via Tail Screening · JMLR · 2025 · 在第 30 页
- Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability · JMLR · 2025 · 在第 30 页
- Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens · JMLR · 2025 · 在第 30 页
- Risk and Optimal Policies in Bandit Experiments · Econometrica · 2025 · 在第 30 页
- Riemannian Bilevel Optimization · JMLR · 2025 · 在第 30 页
- Reward-Directed Score-Based Diffusion Models via q-Learning · JMLR · 2025 · 在第 30 页
- Relaxed Gaussian Process Interpolation: a Goal-Oriented Approach to Bayesian Optimization · JMLR · 2025 · 在第 30 页
- Proper losses regret at least 1/2-order · JMLR · 2025 · 在第 31 页
- Optimizing Return Distributions with Distributional Dynamic Programming · JMLR · 2025 · 在第 31 页
- Optimization Over a Probability Simplex · JMLR · 2025 · 在第 31 页
- Optimal and Efficient Algorithms for Decentralized Online Convex Optimization · JMLR · 2025 · 在第 31 页
- Optimal Decentralized Composite Optimization for Strongly Convex Functions · JMLR · 2025 · 在第 32 页
- Optimal Complexity in Byzantine-Robust Distributed Stochastic Optimization with Data Heterogeneity · JMLR · 2025 · 在第 32 页
- Online Quantile Regression · JMLR · 2025 · 在第 32 页
- On the Utility of Equal Batch Sizes for Inference in Stochastic Gradient Descent · JMLR · 2025 · 在第 32 页
- On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension · JMLR · 2025 · 在第 32 页
- On Global and Local Convergence of Iterative Linear Quadratic Optimization Algorithms for Discrete Time Nonlinear Control · JMLR · 2025 · 在第 32 页
- On Adaptive Stochastic Optimization for Streaming Data: A Newton's Method with O(dN) Operations · JMLR · 2025 · 在第 32 页
- Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning · JMLR · 2025 · 在第 32 页
- Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles · JMLR · 2025 · 在第 32 页
- Mixing Times and Privacy Analysis for the Projected Langevin Algorithm under a Modulus of Continuity · JMLR · 2025 · 在第 32 页
- Mean-Field Variational Inference via Wasserstein Gradient Flow · JMLR · 2025 · 在第 33 页
- Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL · JMLR · 2025 · 在第 33 页
- Losing Momentum in Continuous-time Stochastic Optimisation · JMLR · 2025 · 在第 33 页
- Lexicographic Lipschitz Bandits: New Algorithms and a Lower Bound · JMLR · 2025 · 在第 33 页
- Learning-to-Optimize with PAC-Bayesian Guarantees: Theoretical Considerations and Practical Implementation · JMLR · 2025 · 在第 33 页
- Imprecise Multi-Armed Bandits: Representing Irreducible Uncertainty as a Zero-Sum Game · JMLR · 2025 · 在第 33 页
- Gradient Equilibrium in Online Learning: Theory and Applications · JMLR · 2025 · 在第 34 页
- Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult · JMLR · 2025 · 在第 34 页
- Global Convergence of Adjoint-Optimized Neural PDEs · JMLR · 2025 · 在第 34 页
- Geometric Operator Learning with Optimal Transport · JMLR · 2025 · 在第 34 页
- FedHB: Hierarchical Bayesian Federated Learning · JMLR · 2025 · 在第 34 页
- Fast Computation of Superquantile-Constrained Optimization Through Implicit Scenario Reduction · JMLR · 2025 · 在第 34 页
- Extremal graphical modeling with latent variables via convex optimization · JMLR · 2025 · 在第 35 页
- Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalities · JMLR · 2025 · 在第 35 页
- Efficiently Escaping Saddle Points in Bilevel Optimization · JMLR · 2025 · 在第 35 页
- Efficient Methods for Non-stationary Online Learning · JMLR · 2025 · 在第 35 页
- Distributed Stochastic Bilevel Optimization: Improved Complexity and Heterogeneity Analysis · JMLR · 2025 · 在第 35 页
- DeepCAVE: A Visualization and Analysis Tool for Automated Machine Learning · JMLR · 2025 · 在第 36 页
- Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity · JMLR · 2025 · 在第 36 页
- Decentralized Asynchronous Optimization with DADAO allows Decoupling and Acceleration · JMLR · 2025 · 在第 36 页
- DRM Revisited: A Complete Error Analysis · JMLR · 2025 · 在第 36 页
- Convergence and Sample Complexity of Natural Policy Gradient Primal-Dual Methods for Constrained MDPs · JMLR · 2025 · 在第 36 页
- Convergence Rates for Non-Log-Concave Sampling and Log-Partition Estimation · JMLR · 2025 · 在第 36 页
- Contextual Bandits with Stage-wise Constraints · JMLR · 2025 · 在第 36 页
- Conditional Wasserstein Distances with Applications in Bayesian OT Flow Matching · JMLR · 2025 · 在第 36 页
- Concentration of Cumulative Reward in Markov Decision Processes · JMLR · 2025 · 在第 36 页
- Client Selection for Federated Policy Optimization with Environment Heterogeneity · JMLR · 2025 · 在第 36 页
- Characterizing Dynamical Stability of Stochastic Gradient Descent in Overparameterized Learning · JMLR · 2025 · 在第 36 页
- BoFire: Bayesian Optimization Framework Intended for Real Experiments · JMLR · 2025 · 在第 37 页
- An Adaptive Parameter-free and Projection-free Restarting Level Set Method for Constrained Convex Optimization Under the Error Bound Condition · JMLR · 2025 · 在第 37 页
- Almost Sure Convergence of Dropout Algorithms for Neural Networks · JMLR · 2025 · 在第 37 页
- Adjusted Expected Improvement for Cumulative Regret Minimization in Noisy Bayesian Optimization · JMLR · 2025 · 在第 37 页
- Adaptive Maximization of Social Welfare · Econometrica · 2025 · 在第 37 页
- Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback · JMLR · 2025 · 在第 37 页
- Actor-Critic learning for mean-field control in continuous time · JMLR · 2025 · 在第 37 页
- Accelerating optimization over the space of probability measures · JMLR · 2025 · 在第 37 页
- A statistical perspective on algorithm unrolling models for inverse problems · JMLR · 2025 · 在第 37 页
- A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs · JMLR · 2025 · 在第 37 页
- A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization · JMLR · 2025 · 在第 38 页
- A Decentralized Proximal Gradient Tracking Algorithm for Composite Optimization on Riemannian Manifolds · JMLR · 2025 · 在第 38 页