Country
Information-theoretic Limits of Online Classification with Noisy Labels
Learning from noisy data is a fundamental problem in many machine learning applications.
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
We demonstrate that plasticity loss is pervasive under domain shift in this regime, and that a number of methods developed to resolve it in other settings fail, sometimes even performing worse than applying no intervention at all. In contrast, we find that a class of "regenerative" methods are able to consistently mitigate plasticity loss in a variety of contexts, including in gridworld tasks and
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
However, the problem of provably editing a DNN to satisfy a property remains challenging.
Improved Particle Approximation Error for Mean Field Neural Networks
Recent works (Chen et al., 2022; Suzuki et al., 2023b) have demonstrated In this work, we improve the dependence on logarithmic Sobolev inequality (LSI) constants in their particle approximation errors which can exponentially deteriorate with the regularization coefficient. One may consider adding Gaussian noise to the gradient descent to make the method more stable.
cdf6f8e9fd9aeaf79b6024caec24f15b-Paper-Datasets_and_Benchmarks_Track.pdf
To ensure quality, all charts and questions are handpicked, curated, and verified by human experts.
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models Ling Y ang 1, Zhaochen Y u
BoT has the potential to surpass Llama3-70B model.
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
HR-based orthogonal fine-tuning is equivalent to an adaptive low-rank adaptation.