Search Results for author:
Found 15 papers, 4 papers with code
HYPO: Hyperspherical Out-of-Distribution Generalization
Out-of-distribution (OOD) generalization is critical for machine learning models deployed in the real world.
Training OOD Detectors in their Natural Habitats
Out-of-distribution (OOD) detection is important for machine learning models deployed in the wild.
BIG-bench Machine Learning
Out of Distribution (OOD) Detection
GALAXY: Graph-based Active Learning at the Extreme
Active learning is a label-efficient approach to train highly effective models while interactively selecting only small subsets of unlabelled data for labelling and training.
Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers
We begin our investigation with the observation that agnostic algorithms \emph{cannot} be minimax-optimal in the realizable setting.
Near Instance Optimal Model Selection for Pure Exploration Linear Bandits
The core of our algorithms is a new optimization problem based on experimental design that leverages the geometry of the action set to identify a near-optimal hypothesis class.
Improved Algorithms for Agnostic Pool-based Active Classification
We consider active learning for binary classification in the agnostic pool-based setting.
High-Dimensional Experimental Design and Kernel Bandits
We also leverage our new approach in a new algorithm for kernelized bandits to obtain state of the art results for regret minimization and pure exploration.
Experimental Design for Regret Minimization in Linear Bandits
In this paper we propose a novel experimental design-based algorithm to minimize regret in online stochastic linear and combinatorial bandits.
Similarity Search for Efficient Active Learning and Search of Rare Concepts
Many active learning and search approaches are intractable for large-scale industrial settings with billions of unlabeled examples.
An Empirical Process Approach to the Union Bound: Practical Algorithms for Combinatorial and Linear Bandits
This paper proposes near-optimal algorithms for the pure-exploration linear bandit problem in the fixed confidence and fixed budget settings.
The True Sample Complexity of Identifying Good Arms
We consider two multi-armed bandit problems with $n$ arms: (i) given an $\epsilon > 0$, identify an arm with mean that is within $\epsilon$ of the largest mean and (ii) given a threshold $\mu_0$ and integer $k$, identify $k$ arms with means larger than $\mu_0$.
Feasible Arm Identification
We introduce the feasible arm identification problem, a pure exploration multi-armed bandit problem where the agent is given a set of $D$-dimensional arms and a polyhedron $P = \{x : A x \leq b \} \subset R^D$.
Decontamination of Mutual Contamination Models
Many machine learning problems can be characterized by mutual contamination models.
Nonparametric Preference Completion
We consider the task of collaborative preference completion: given a pool of items, a pool of users and a partially observed item-user rating matrix, the goal is to recover the \emph{personalized ranking} of each user over all of the items.
A Mutual Contamination Analysis of Mixed Membership and Partial Label Models
We examine the decontamination problem in two mutual contamination models that describe popular machine learning tasks: recovering the base distributions up to a permutation in a mixed membership model, and recovering the base distributions exactly in a partial label model for classification.
