research
∙
03/13/2023
Meet in the Middle: A New Pre-training Paradigm
Most language models (LMs) are trained and applied in an autoregressive ...
share
research
∙
10/19/2022
Anytime-valid off-policy inference for contextual bandits
Contextual bandit algorithms are ubiquitous tools for active sequential ...
research
∙
12/06/2021
Contextual Bandit Applications in Customer Support Bot
Virtual support agents have grown in popularity as a way for businesses ...
research
∙
02/18/2021
Off-policy Confidence Sequences
We develop confidence bounds that hold uniformly over time for off-polic...
research
∙
06/07/2019
Empirical Likelihood for Contextual Bandits
We apply empirical likelihood techniques to contextual bandit policy val...
research
∙
05/06/2019
Lessons from Real-World Reinforcement Learning in a Customer Support Bot
In this work, we describe practical lessons we have learned from success...
research
∙
06/15/2016
Logarithmic Time One-Against-Some
We create a new online reduction of multiclass classification to binary ...
research
∙
02/05/2016
Active Information Acquisition
We propose a general framework for sequential and dynamic acquisition of...
research
∙
11/10/2015
A Hierarchical Spectral Method for Extreme Classification
Extreme classification problems are multiclass and multilabel classifica...
research
∙
11/13/2014
A Randomized Algorithm for CCA
We present RandomizedCCA, a randomized algorithm for computing canonical...
research
∙
10/07/2013
Least Squares Revisited: Scalable Approaches for Multi-class Prediction
This work provides simple algorithms for multi-class (and multi-label) p...
research
∙
10/07/2013
Discriminative Features via Generalized Eigenvectors
Representing examples in a way that is compatible with the underlying cl...
research
∙
06/07/2013
Loss-Proportional Subsampling for Subsequent ERM
We propose a sampling scheme suitable for reducing a data set prior to s...
research
∙
06/13/2011