2 papers
cs.LG2026
OR Else: A Differentiable Trust Region for Policy Optimization
Chinmay Rane, Kanishka Tyagi, Michael Manry
PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative. We as…
cs.LG2023
Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
Chinmay Rane, Kanishka Tyagi, Michael Manry
Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge…