no code implementations • 8 Mar 2017 • Peter L. Bartlett, Nick Harvey, Chris Liaw, Abbas Mehrabian
We prove new upper and lower bounds on the VC-dimension of deep neural networks with the ReLU activation function.
no code implementations • 6 Jun 2017 • Hassan Ashtiani, Shai Ben-David, Abbas Mehrabian
Let $\mathcal F$ be an arbitrary class of probability distributions, and let $\mathcal{F}^k$ denote the class of $k$-mixtures of elements of $\mathcal F$.
no code implementations • 14 Oct 2017 • Hassan Ashtiani, Shai Ben-David, Nick Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan
We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance.
no code implementations • 11 Jan 2018 • Hassan Ashtiani, Abbas Mehrabian
Density estimation is an interdisciplinary topic at the intersection of statistics, theoretical computer science and machine learning.
no code implementations • 18 Jun 2018 • Luc Devroye, Abbas Mehrabian, Tommy Reddad
Let $G$ be an undirected graph with $m$ edges and $d$ vertices.
no code implementations • 25 Aug 2018 • Gabor Lugosi, Abbas Mehrabian
We give the first theoretical guarantees for the second model: an algorithm with a logarithmic regret, and an algorithm with a square-root regret type that does not depend on the gaps between the means.
no code implementations • NeurIPS 2018 • Hassan Ashtiani, Shai Ben-David, Nicholas Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan
We prove that ϴ(k d^2 / ε^2) samples are necessary and sufficient for learning a mixture of k Gaussians in R^d, up to error ε in total variation distance.
no code implementations • 4 Feb 2019 • Etienne Boursier, Emilie Kaufmann, Abbas Mehrabian, Vianney Perchet
We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward.
1 code implementation • 11 Oct 2019 • Sharan Vaswani, Abbas Mehrabian, Audrey Durand, Branislav Kveton
We propose $\tt RandUCB$, a bandit strategy that builds on theoretically derived confidence intervals similar to upper confidence bound (UCB) algorithms, but akin to Thompson sampling (TS), it uses randomization to trade off exploration and exploitation.
no code implementations • 11 Oct 2019 • Hossein Esfandiari, Amin Karbasi, Abbas Mehrabian, Vahab Mirrokni
We present simple and efficient algorithms for the batched stochastic multi-armed bandit and batched stochastic linear bandit problems.
no code implementations • 6 Nov 2023 • Abbas Mehrabian, Ankit Anand, Hyunjik Kim, Nicolas Sonnerat, Matej Balog, Gheorghe Comanici, Tudor Berariu, Andrew Lee, Anian Ruoss, Anna Bulanova, Daniel Toyama, Sam Blackwell, Bernardino Romera Paredes, Petar Veličković, Laurent Orseau, Joonkyung Lee, Anurag Murty Naredla, Doina Precup, Adam Zsolt Wagner
This work studies a central extremal graph theory problem inspired by a 1975 conjecture of Erd\H{o}s, which aims to find graphs with a given size (number of nodes) that maximize the number of edges without having 3- or 4-cycles.