
Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise
We develop a computationallyefficient PAC active learning algorithm for...
read it

Multitask Bandit Learning through Heterogeneous Feedback Aggregation
In many realworld applications, multiple agents seek to learn how to pe...
read it

Active Online Domain Adaptation
Online machine learning systems need to adapt to domain shifts. Meanwhil...
read it

Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
We study stochastic structured bandits for minimizing regret. The fact t...
read it

Efficient Contextual Bandits with Continuous Actions
We create a computationally tractable algorithm for contextual bandits w...
read it

AttributeEfficient Learning of Halfspaces with Malicious Noise: NearOptimal Label Complexity and Noise Tolerance
This paper is concerned with computationally efficient learning of homog...
read it

Efficient active learning of sparse halfspaces with arbitrary bounded noise
In this work we study active learning of homogeneous ssparse halfspaces...
read it

Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
We design a new algorithm for batch active learning with deep neural net...
read it

Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
We study the problem of efficient online multiclass linear classificatio...
read it

Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
We study contextual bandit learning with an abstract policy class and co...
read it

Warmstarting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
We investigate the feasibility of learning from both fullylabeled super...
read it

Efficient active learning of sparse halfspaces
We study the problem of efficient PAC active learning of homogeneous lin...
read it

Spectral Learning of Binomial HMMs for DNA Methylation Data
We consider learning parameters of Binomial Hidden Markov Models, which ...
read it

Efficient Online Bandit Multiclass Learning with Õ(√(T)) Regret
We present an efficient secondorder algorithm with Õ(1/η√(T)) regret fo...
read it

Revisiting Perceptron: Efficient and LabelOptimal Learning of Halfspaces
It has been a longstanding problem to efficiently learn a halfspace usi...
read it

Search Improves Label for Active Learning
We investigate active learning with access to two distinct oracles: Labe...
read it

Active Learning from Weak and Strong Labelers
An active learner is given a hypothesis class, a large set of unlabeled ...
read it

Spectral Learning of Large Structured HMMs for Comparative Epigenomics
We develop a latent variable model and an efficient spectral algorithm m...
read it

Beyond Disagreementbased Agnostic Active Learning
We study agnostic active learning, where the goal is to learn a classifi...
read it
Chicheng Zhang
is this you? claim profile