Statistical Learning
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
The remarkable success of transformers in sequence modeling tasks, spanning various applications in natural language processing and computer vision, is attributed to the critical role of self-attention.
From Causal to Concept-Based Representation Learning
A key question in this growing field is to provide rigorous conditions under which latent factors can be identified and thus, potentially learned.
Bayesian Learning via Q-Exponential Process
Regularization is one of the most fundamental topics in optimization, statistics and machine learning.
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening Guy Bar-Shalom
This paper introduces a new Subgraph GNN framework to address these issues.
Training Chain-of-Thought via Latent-Variable Inference Du Phan Matthew D. Hoffman
One can also improve LLMs' performance on a specific task by
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encodings Laxman Dhulipala Google Research and UMD Majid Hadian Google DeepMind Rajesh Jayaram
Neural embedding models have become a fundamental component of modern information retrieval (IR) pipelines.
Responsible AI (RAI) Games and Ensembles
In this work, we provide a general framework for studying these problems, which we refer to as Responsible AI (RAI) games .
An Information Theoretic Perspective on Conformal Prediction
More precisely, we prove three different ways to upper bound the intrinsic uncertainty, as described by the conditional entropy of the target variable given the inputs, by combining CP with information theoretical inequalities.