Aryan Mokhtari

Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization COLT 2026 Statistical Learning from Attribution Sets COLT 2026 Learning Mixtures of Experts with EM: A Mirror Descent Perspective ICML 2025 On the Crucial Role of Initialization for Matrix Factorization ICLR 2025 Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization COLT 2025 Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization NeurIPS 2024 An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization NeurIPS 2024 In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness NeurIPS 2024 Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate AISTATS 2024 Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search NeurIPS 2024 Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks ICML 2024 Stochastic Newton Proximal Extragradient Method NeurIPS 2024 Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization NeurIPS 2023 A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem AISTATS 2023 Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing NeurIPS 2023 InfoNCE Loss Provably Learns Cluster-Preserving Representations COLT 2023 Online Learning Guided Curvature Approximation: A Quasi-Newton Method with Global Non-Asymptotic Superlinear Convergence COLT 2023 Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem NeurIPS 2023 FedAvg with Fine Tuning: Local Updates Lead to Representation Learning NeurIPS 2022 Future gradient descent for adapting the temporal shifting data distribution in online recommendation systems UAI 2022 MAML and ANIL Provably Learn Representations ICML 2022 Minimax Optimization: The Case of Convex-Submodular AISTATS 2022 Sharpened Quasi-Newton Methods: Faster Superlinear Rate and Larger Local Convergence Neighborhood ICML 2022 The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance COLT 2022 Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach NeurIPS 2021 Exploiting Shared Representations for Personalized Federated Learning ICML 2021 Federated Learning with Compression: Unified Analysis and Sharp Guarantees AISTATS 2021 Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks NeurIPS 2021 On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning NeurIPS 2021 A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning JMLR 2020 A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach AISTATS 2020 DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate AISTATS 2020 Efficient Distributed Hessian Free Algorithm for Large-scale Empirical Risk Minimization via Accumulating Sample Strategy AISTATS 2020 FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization AISTATS 2020 One Sample Stochastic Frank-Wolfe AISTATS 2020 On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms AISTATS 2020 Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach NeurIPS 2020 Quantized Decentralized Stochastic Learning over Directed Graphs ICML 2020 Quantized Frank-Wolfe: Faster Optimization, Lower Communication, and Projection Free AISTATS 2020 Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking NeurIPS 2020 Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization JMLR 2020 Submodular Meta-Learning NeurIPS 2020 Task-Robust Model-Agnostic Meta-Learning NeurIPS 2020 Efficient Nonconvex Empirical Risk Minimization via Adaptive Sample Size Methods AISTATS 2019 Robust and Communication-Efficient Collaborative Learning NeurIPS 2019 Stochastic Continuous Greedy ++: When Upper and Lower Bounds Match NeurIPS 2019 Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap AISTATS 2018 Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings ICML 2018 Direct Runge-Kutta Discretization Achieves Acceleration NeurIPS 2018 Escaping Saddle Points in Constrained Optimization NeurIPS 2018 Large Scale Empirical Risk Minimization via Truncated Adaptive Newton Method AISTATS 2018 Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication ICML 2018 First-Order Adaptive Sample Size Methods to Reduce Complexity of Empirical Risk Minimization NeurIPS 2017 Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy NeurIPS 2016 DSA: Decentralized Double Stochastic Averaging Gradient Algorithm JMLR 2016 Global Convergence of Online Limited Memory BFGS JMLR 2015