3 citations · 6 across the 8 of their papers we have counts for
9 papers
M-duality in fixed-point problems for general normed spaces
Jongmin Lee, Sangyeop Woo, Ernest K. Ryu
Solving fixed-point problems by reducing residual bounds is one of the central approaches in fixed-point iteration, and, in particular, the Halpern iteration is known to effectivel…
Policy Gradient Algorithms in Average-Reward Multichain MDPs
Jongmin Lee, Ernest K. Ryu
While there is an extensive body of research analyzing policy gradient methods for discounted cumulative-reward MDPs, prior work on policy gradient methods for average-reward MDPs…
Finite-Time Bounds for Average-Reward Fitted Q-Iteration
Jongmin Lee, Ernest K. Ryu
Although there is an extensive body of work characterizing the sample complexity of discounted-return offline RL with function approximations, prior work on the average-reward sett…
Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs
Jongmin Lee, Ernest K. Ryu
The classical policy gradient method is the theoretical and conceptual foundation of modern policy-based reinforcement learning (RL) algorithms. Most rigorous analyses of such meth…
Deflated Dynamics Value Iteration
Jongmin Lee, Amin Rakhsha, Ernest K. Ryu +1
The Value Iteration (VI) algorithm is an iterative procedure to compute the value function of a Markov decision process, and is the basis of many reinforcement learning (RL) algori…
Accelerating Value Iteration with Anchoring
Jongmin Lee, Ernest K. Ryu
Value Iteration (VI) is foundational to the theory and practice of modern reinforcement learning, and it is known to converge at a -rate, where is the discoun…
Convergence Analyses of Davis-Yin Splitting via Scaled Relative Graphs
Jongmin Lee, Soheun Yi, Ernest K. Ryu
Davis-Yin splitting (DYS) has found a wide range of applications in optimization, but its linear rates of convergence have not been studied extensively. The scaled relative graph (…
Neural Tangent Kernel Analysis of Deep Narrow Neural Networks
Jongmin Lee, Joo Young Choi, Ernest K. Ryu +1
The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently ad…
A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast
Jongmin Lee, Chanwoo Park, Ernest K. Ryu
Since Nesterov's seminal 1983 work, many accelerated first-order optimization methods have been proposed, but their analyses lacks a common unifying structure. In this work, we ide…