103 citations · 311 across the 16 of their papers we have counts for
Showing 2021Show all
3 papers · 1 filter
cs.LG2021★ 1 cited
Actor-critic is implicitly biased towards high entropy optimal policies
Yuzheng Hu, Ziwei Ji, Matus Telgarsky
We show that the simplest actor-critic method -- a linear softmax policy updated with TD through interaction with a linear MDP, but featuring no explicit regularization or explorat…
cs.LG2021★ 2 cited
Fast Margin Maximization via Dual Acceleration
Ziwei Ji, Nathan Srebro, Matus Telgarsky
We present and analyze a momentum-based gradient method for training linear classifiers with an exponentially-tailed loss (e.g., the exponential or logistic loss), which maximizes…
cs.LG2021★ 9 cited
Early-stopped neural networks are consistent
Ziwei Ji, Justin D. Li, Matus Telgarsky
This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is…