no code implementations • 8 Apr 2024 • Ali Mortazavi, Junhao Lin, Nishant A. Mehta
In this work, our goal is to design an algorithm for the selfish experts problem that is incentive-compatible (IC, or \emph{truthful}), meaning each expert's best strategy is to report truthfully, while also ensuring the algorithm enjoys sublinear regret with respect to the expert with the best belief.
no code implementations • 2 Mar 2024 • Quan Nguyen, Nishant A. Mehta
In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(K\sqrt{TA\ln{K}})$, obtained indirectly via minimizing internal sleeping regrets.
no code implementations • 6 May 2023 • Nishant A. Mehta
In the setting of stochastic online learning with undirected feedback graphs, Lykouris et al. (2020) previously analyzed the pseudo-regret of the upper confidence bound-based algorithm UCB-N and the Thompson Sampling-based algorithm TS-N.
1 code implementation • 11 Jan 2023 • Quan Nguyen, Nishant A. Mehta
We prove a minimax lower bound of $\Omega(K\sqrt{DSAH})$ on the regret of any learning algorithm and an instance-specific lower bound of $\Omega(\frac{K}{\lambda^2})$ in sample complexity for a class of uniformly-good cluster-then-learn algorithms.
no code implementations • NeurIPS 2021 • Cristóbal Guzmán, Nishant A. Mehta, Ali Mortazavi
Much of the work in online learning focuses on the study of sublinear upper bounds on the regret.
no code implementations • 16 Feb 2021 • Bingshan Hu, Zhiming Huang, Nishant A. Mehta, Nidhi Hegde
In this paper, we study differentially private online learning problems in a stochastic environment under both bandit and full information feedback.
no code implementations • 6 Mar 2020 • P Sharoff, Nishant A. Mehta, Ravi Ganti
We consider a sequential decision-making problem where an agent can take one action at a time and each action has a stochastic temporal extent, i. e., a new action cannot be taken until the previous one is finished.
no code implementations • NeurIPS 2019 • Hamid Shayestehmanesh, Sajjad Azami, Nishant A. Mehta
In both cases, we provide matching upper and lower bounds on the ranking regret in the fully adversarial setting.
no code implementations • 27 Feb 2018 • Rafael Frongillo, Nishant A. Mehta, Tom Morgan, Bo Waggoner
Recent work introduced loss functions which measure the error of a prediction based on multiple simultaneous observations or outcomes.
no code implementations • 21 Oct 2017 • Peter D. Grünwald, Nishant A. Mehta
Our first main result bounds excess risk in terms of the new complexity.
no code implementations • 12 Sep 2016 • Nishant A. Mehta, Alistair Rendell, Anish Varghese, Christfried Webers
The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods.
no code implementations • 4 May 2016 • Nishant A. Mehta
We present an algorithm for the statistical learning setting with a bounded exp-concave loss in $d$ dimensions that obtains excess risk $O(d \log(1/\delta)/n)$ with probability at least $1 - \delta$.
no code implementations • 1 May 2016 • Peter D. Grünwald, Nishant A. Mehta
For general loss functions, our bounds rely on two separate conditions: the $v$-GRIP (generalized reversed information projection) conditions, which control the lower tail of the excess loss; and the newly introduced witness condition, which controls the upper tail.
no code implementations • 9 Jul 2015 • Tim van Erven, Peter D. Grünwald, Nishant A. Mehta, Mark D. Reid, Robert C. Williamson
For bounded losses, we show how the central condition enables a direct proof of fast rates and we prove its equivalence to the Bernstein condition, itself a generalization of the Tsybakov margin condition, both of which have played a central role in obtaining fast rates in statistical learning.
no code implementations • NeurIPS 2014 • Nishant A. Mehta, Robert C. Williamson
In the non-statistical prediction with expert advice setting, there is an analogous slow and fast rate phenomenon, and it is entirely characterized in terms of the mixability of the loss $\ell$ (there being no role there for $\mathcal{F}$ or $\mathsf{P}$).