Statistical Learning
Transformers are Minimax Optimal Nonparametric In-Context Learners Juno Kim 1,2 T ai Nakamaki 1 T aiji Suzuki 1,2 1 University of Tokyo 2
Large language models (LLMs) have demonstrated remarkable capabilities in understanding and generating natural language data.
SMF_NeurIPS_2023-6
Our framework applies to a wide range of SMF-type problems for multi-class classification with auxiliary features.
Normalization and effective learning rates in reinforcement learning Clare Lyle
Layer normalization has demonstrated remarkable effectiveness at preventing plasticity loss in continual and reinforcement learning (RL), though the precise reasons for this effectiveness remain mysterious.
Parallel-mentoring for Offline Model-based Optimization Can (Sam) Chen
We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores.
Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families
Recent works in V ariational Inference have examined alternative criteria to the commonly used exclusive Kullback-Leibler divergence.