274 citations · 480 across the 29 of their papers we have counts for
24 papers · 1 filter
Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
Hao Qin, Kwang-Sung Jun, Chicheng Zhang
We study -armed bandit problems where the reward distributions of the arms are all supported on the interval. It has been a challenge to design regret-efficient randomiz…
On Efficient Online Imitation Learning via Classification
Yichen Li, Chicheng Zhang
Imitation learning (IL) is a general learning paradigm for tackling sequential decision-making problems. Interactive imitation learning, where learners can interactively query for…
Thompson Sampling for Robust Transfer in Multi-Task Bandits
Zhi Wang, Chicheng Zhang, Kamalika Chaudhuri
We study the problem of online multi-task learning where the tasks are performed within similar but not necessarily identical multi-armed bandit environments. In particular, we stu…
Active Fairness Auditing
Tom Yan, Chicheng Zhang
The fast spreading adoption of machine learning (ML) by companies across industries poses significant regulatory challenges. One such challenge is scalability: how can regulatory b…
Margin-distancing for safe model explanation
Tom Yan, Chicheng Zhang
The growing use of machine learning models in consequential settings has highlighted an important and seemingly irreconcilable tension between transparency and vulnerability to gam…
SIM-ECG: A Signal Importance Mask-driven ECGClassification System
Dharma KC, Chicheng Zhang, Chris Gniady +2
Heart disease is the number one killer, and ECGs can assist in the early diagnosis and prevention of deadly outcomes. Accurate ECG interpretation is critical in detecting heart dis…
Provably Efficient Multi-Task Reinforcement Learning with Model Transfer
Chicheng Zhang, Zhi Wang
We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of play…
Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise
Chicheng Zhang, Yinan Li
We give a computationally-efficient PAC active learning algorithm for -dimensional homogeneous halfspaces that can tolerate Massart noise (Massart and Nédélec, 2006) and Tsybako…
Multitask Bandit Learning Through Heterogeneous Feedback Aggregation
Zhi Wang, Chicheng Zhang, Manish Kumar Singh +2
In many real-world applications, multiple agents seek to learn how to perform highly related yet slightly different tasks in an online bandit learning protocol. We formulate this p…
Active Online Learning with Hidden Shifting Domains
Yining Chen, Haipeng Luo, Tengyu Ma +1
Online machine learning systems need to adapt to domain shifts. Meanwhile, acquiring label at every timestep is expensive. We propose a surprisingly simple algorithm that adaptivel…
Crush Optimism with Pessimism: Structured Bandits Beyond Asymptotic Optimality
Kwang-Sung Jun, Chicheng Zhang
We study stochastic structured bandits for minimizing regret. The fact that the popular optimistic algorithms do not achieve the asymptotic instance-dependent regret optimality (as…
Efficient Contextual Bandits with Continuous Actions
Maryam Majzoubi, Chicheng Zhang, Rajan Chari +3
We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised…
Efficient active learning of sparse halfspaces with arbitrary bounded noise
Chicheng Zhang, Jie Shen, Pranjal Awasthi
We study active learning of homogeneous -sparse halfspaces in under the setting where the unlabeled data distribution is isotropic log-concave and each label is f…
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy +2
We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of…
Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case
Alina Beygelzimer, Dávid Pál, Balázs Szörényi +3
We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of classes and lie in the -dimensional Eucli…
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
Chicheng Zhang, Alekh Agarwal, Hal Daumé +2
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying le…
Efficient active learning of sparse halfspaces
Chicheng Zhang
We study the problem of efficient PAC active learning of homogeneous linear classifiers (halfspaces) in , where the goal is to learn a halfspace with low error using…
Spectral Learning of Binomial HMMs for DNA Methylation Data
Chicheng Zhang, Eran A. Mukamel, Kamalika Chaudhuri
We consider learning parameters of Binomial Hidden Markov Models, which may be used to model DNA methylation data. The standard algorithm for the problem is EM, which is computatio…
Efficient Online Bandit Multiclass Learning with Regret
Alina Beygelzimer, Francesco Orabona, Chicheng Zhang
We present an efficient second-order algorithm with regret for the bandit online multiclass problem. The regret bound holds simultaneously with respe…
Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces
Songbai Yan, Chicheng Zhang
It has been a long-standing problem to efficiently learn a halfspace using as few labels as possible in the presence of noise. In this work, we propose an efficient Perceptron-base…
The Extended Littlestone's Dimension for Learning with Mistakes and Abstentions
Chicheng Zhang, Kamalika Chaudhuri
This paper studies classification with an abstention option in the online setting. In this setting, examples arrive sequentially, the learner is given a hypothesis class $\mathcal…
Search Improves Label for Active Learning
Alina Beygelzimer, Daniel Hsu, John Langford +1
We investigate active learning with access to two distinct oracles: Label (which is standard) and Search (which is not). The Search oracle models the situation where a human search…
Active Learning from Weak and Strong Labelers
Chicheng Zhang, Kamalika Chaudhuri
An active learner is given a hypothesis class, a large set of unlabeled examples and the ability to interactively query labels to an oracle of a subset of these examples; the goal…
Beyond Disagreement-based Agnostic Active Learning
Chicheng Zhang, Kamalika Chaudhuri
We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no…