Deep Learning
Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies Oscar Li1, James Harrison, Jascha Sohl-Dickstein, Virginia Smith
First-order optimization methods are a foundational tool in machine learning.
On the Power of Decision Trees in Auto-Regressive Language Modeling
Tree-based models, particularly favored for handling tabular data (Grinsztajn et al., 2022), continue
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing Simon Buchholz
Therefore, it's important to study whether we can and also how to
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
Deep learning succeeds by doing hierarchical feature learning, yet tuning hyper-parameters (HP) such as initialization scales, learning rates etc., only give indirect
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs Rui Y ang 1 Ruomeng Ding 2 Yong Lin
While previous research has advocated for constraining policy optimization, our study introduces a novel approach to enhance the reward model's