Search Results for author:
Found 9 papers, 1 papers with code
Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure
Our characterization identifies a partial identifiability property of the problem instance as the necessary and sufficient condition for the asymptotic success.
Principal-Agent Multitasking: the Uniformity of Optimal Contracts and its Efficient Learning via Instrumental Regression
I then study a setting where the marginal utility of each task is unknown so that the optimal contract must be learned or estimated with observational data.
New Perspectives in Online Contract Design
This work studies the repeated principal-agent problem from an online learning perspective.
Contextual Bandits with Online Neural Regression
Based on such a perturbed prediction, we show a ${\mathcal{O}}(\log T)$ regret for online regression with both squared loss and KL loss, and subsequently convert these respectively to $\tilde{\mathcal{O}}(\sqrt{KT})$ and $\tilde{\mathcal{O}}(\sqrt{KL^*} + K)$ regret for NeuCB, where $L^*$ is the loss of the best policy.
Corruption-Robust Lipschitz Contextual Search
In a total of $C$ rounds, the signal may be corrupted, though the value of $C$ is \emph{unknown} to the learner.
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
Near Optimal Adversarial Attacks on Stochastic Bandits and Defenses with Smoothed Responses
I design attack strategies against UCB and Thompson Sampling that only spend $\widehat{O}(\sqrt{\log T})$ cost.
Notes on Worst-case Inefficiency of Gradient Descent Even in R^2
In non-convex settings, it has been shown that gradient descent is able to escape saddle points asymptotically and converge to local minimizers [Lee et.
