Max Simchowitz

Publications by Year

Research Areas

Advanced Bandit Algorithms Research, Reinforcement Learning in Robotics, Machine Learning and Algorithms, Model Reduction and Neural Networks, Sparse and Compressive Sensing Techniques

Most-Cited Works

• Gradient Descent Only Converges to Minimizers(2016)
• Low-rank solutions of linear matrix equations via procrustes flow(2016)
• → First-order methods almost always avoid strict saddle points(2019)143 cited
• → Gradient Descent Converges to Minimizers(2016)123 cited
• → Learning Without Mixing: Towards A Sharp Analysis of Linear System\n Identification(2018)116 cited
• → First-order Methods Almost Always Avoid Saddle Points(2017)76 cited
• Improper Learning for Non-Stochastic Control(2020)
• → Corruption-Robust Exploration in Episodic Reinforcement Learning(2024)38 cited