Jun-Kun Wang
Email: jkw005 [at] ucsd [dot] edu Publications: *Corresponding Author/*Presenting Author No-Regret Dynamics in the Fenchel Game: A Unified Framework for Algorithmic Convex Optimization. Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation Provable Acceleration of Heavy Ball beyond Quadratics for a class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out Understanding Modern Techniques in Optimization: Frank-Wolfe, Nesterov's Momentum, and Polyak's Momentum. A Modular Analysis of Provable Acceleration via Polyak's momentum: Training a Wide ReLU Network and a Deep Linear Network Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron Escape Saddle Points Faster with Stochastic Momentum. Online Linear Optimization with Sparsity Constraints Revisiting Projection-Free Optimization For Strongly Convex Constraint Sets Acceleration through Optimistic No-Regret Dynamics Faster Rates for Convex-Concave Games On Frank-Wolfe and Equilibrium Computation Efficient Sampling-based ADMM for Distributed Data Parallel Least-Squares Policy Iteration Robust Inverse Covariance Estimation under Noisy Measurements Techical Reports: 1 Quickly Finding a Benign Region via Heavy Ball Momentum in Non-Convex Optimization Reviewer of NeurIPS 2016,2017,2018,2019,2020,2021,2022, of ICML 2017,2018,2019,2020,2021,2022, of COLT 2017,2018,2019,2020,2021,2022, of ALT 2017,2018,2019,2020,2022, of ICLR 2021,2022 |