Search Results for author:
Found 16 papers, 0 papers with code
Approximating Continuous Functions by ReLU Nets of Minimal Width
Specifically, we answer the following question: for a fixed $d_{in}\geq 1,$ what is the minimal width $w$ so that neural nets with ReLU activations, input dimension $d_{in}$, hidden layer widths at most $w,$ and arbitrary depth can approximate any continuous, real-valued function of $d_{in}$ variables arbitrarily well?
First-Order Bayesian Regret Analysis of Thompson Sampling
Second we replace the entropy over combinatorial actions by a coordinate entropy, which allows us to obtain the first optimal worst-case bound for Thompson Sampling in the combinatorial setting.
Non-Stochastic Multi-Player Multi-Armed Bandits: Optimal Rate With Collision Information, Sublinear Without
We consider the non-stochastic version of the (cooperative) multi-player multi-armed bandit problem.
The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity
The performance loss due to incentives is therefore limited to the initial rounds when these data points are collected.
Online Multiserver Convex Chasing and Optimization
We introduce the problem of $k$-chasing of convex functions, a simultaneous generalization of both the famous k-server problem in $R^d$, and of the problem of chasing convex bodies and functions.
Algorithmic pure states for the negative spherical perceptron
In this paper we design an efficient algorithm which, given oracle access to the solution of the Parisi variational principle, exploits this conjectured FRSB structure for $\kappa<0$ and outputs a vector $\hat{\sigma}$ satisfying $\langle g_a , \hat{\sigma}\rangle \ge \kappa \sqrt{N}$ for all $1\le a \le M$ and lying on a sphere of non-trivial radius $\sqrt{\bar{q} N}$, where $\bar{q} \in (0, 1)$ is the right-end of the support of the associated Parisi measure.
Probability Data Structures and Algorithms Mathematical Physics Mathematical Physics
Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions
We consider the cooperative multi-player version of the stochastic multi-armed bandit problem.
Metric Transforms and Low Rank Matrices via Representation Theory of the Real Hyperrectangle
This completes the theory of Manhattan to Manhattan metric transforms initiated by Assouad in 1980.
A Universal Law of Robustness via Isoperimetry
Classically, data interpolation with a parametrized model class is possible as long as the number of parameters is larger than the number of equations to be satisfied.
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
Domain generalization aims at performing well on unseen test environments with data from a limited number of training environments.
The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication
We ask whether it is possible to obtain optimal instance-dependent regret $\tilde{O}(1/\Delta)$ where $\Delta$ is the gap between the $m$-th and $m+1$-st best arms.
When Does Adaptivity Help for Quantum State Learning?
We give an adaptive algorithm that outputs a state which is $\gamma$-close in infidelity to $\rho$ using only $\tilde{O}(d^3/\gamma)$ copies, which is optimal for incoherent measurements.
Asymptotically Optimal Pure Exploration for Infinite-Armed Bandits
For fixed budget, we show the asymptotically optimal sample complexity as $\delta\to 0$ is $c^{-1}\log(1/\delta)\big(\log\log(1/\delta)\big)^2$ to leading order.
On Size-Independent Sample Complexity of ReLU Networks
We study the sample complexity of learning ReLU neural networks from the point of view of generalization.
Incentivizing Exploration with Linear Contexts and Combinatorial Actions
We advance the study of incentivized bandit exploration, in which arm choices are viewed as recommendations and are required to be Bayesian incentive compatible.
No Free Prune: Information-Theoretic Barriers to Pruning at Initialization
We put forward a theoretical explanation for this, based on the model's effective parameter count, $p_\text{eff}$, given by the sum of the number of non-zero weights in the final network and the mutual information between the sparsity mask and the data.
