Search Results for author:
Found 17 papers, 1 papers with code
From Bandits to Experts: A Tale of Domination and Independence
We consider the partial observability model for multi-armed bandits, introduced by Mannor and Shamir.
Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback
This naturally models several situations where the losses of different actions are related, and knowing the loss of one action provides information on the loss of other actions.
Online Learning with Feedback Graphs: Beyond Bandits
We study a general class of online learning problems where the feedback is specified by a graph.
Optimal compression of approximate inner products and dimension reduction
On the positive side, we provide a randomized polynomial time algorithm for a bipartite variant of the Johnson-Lindenstrauss lemma in which scalar products are approximated up to an additive error of at most $\varepsilon$.
Metric Geometry Combinatorics
Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues
In this work we derive a variant of the classic Glivenko-Cantelli Theorem, which asserts uniform convergence of the empirical Cumulative Distribution Function (CDF) to the CDF of the underlying distribution.
A graph-theoretic approach to multitasking
A key feature of neural network architectures is their ability to support the simultaneous interaction among large numbers of units in the learning and processing of representations.
Private PAC learning implies finite Littlestone dimension
We show that every approximately differentially private learning algorithm (possibly improper) for a class $H$ with Littlestone dimension~$d$ requires $\Omega\bigl(\log^*(d)\bigr)$ examples.
Limits of Private Learning with Access to Public Data
We consider learning problems where the training set consists of two types of examples: private and public.
Boosting Simple Learners
(ii) Expressivity: Which tasks can be learned by boosting weak hypotheses from a bounded VC class?
Closure Properties for Private Classification and Online Prediction
Let~$\cH$ be a class of boolean functions and consider a {\it composed class} $\cH'$ that is derived from~$\cH$ using some arbitrary aggregation rule (for example, $\cH'$ may be the class of all 3-wise majority-votes of functions in $\cH$).
Divisible subdivisions
We prove that for every graph $H$ of maximum degree at most $3$ and for every positive integer $q$ there is a finite $f=f(H, q)$ such that every $K_f$-minor contains a subdivision of $H$ in which every edge is replaced by a path whose length is divisible by $q$.
Combinatorics 05C53, 05C83, 05C38
Adversarial Laws of Large Numbers and Optimal Regret in Online Classification
Laws of large numbers guarantee that given a large enough sample from some population, the measure of any fixed sub-population is well-estimated by its frequency in the sample.
Dominance Solvability in Random Games
We study the effectiveness of iterated elimination of strictly-dominated actions in random games.
A Theory of PAC Learnability of Partial Concept Classes
In fact we exhibit easy-to-learn partial concept classes which provably cannot be captured by the traditional PAC theory.
A Unified Characterization of Private Learnability via Graph Theory
Learning $\mathcal{H}$ under pure DP is captured by the fractional clique number of $G$.
Optimal Sample Complexity of Contrastive Learning
Contrastive learning is a highly successful technique for learning representations of data from labeled tuples, specifying the distance relations within the tuple.
