Search Results for author:
Found 13 papers, 1 papers with code
Learnability Gaps of Strategic Classification
We essentially show that any learnable class is also strategically learnable: we first consider a fully informative setting, where the manipulation structure (which is modeled by a manipulation graph $G^\star$) is known and during training time the learner has access to both the pre-manipulation data and post-manipulation data.
On the Effect of Defections in Federated Learning and How to Prevent Them
Federated learning is a machine learning protocol that enables a large population of agents to collaborate over multiple rounds to produce a single consensus model.
Incentivized Collaboration in Active Learning
In collaborative active learning, where multiple agents try to learn labels from a common hypothesis, we introduce an innovative framework for incentivized collaboration.
Strategic Classification under Unknown Personalized Manipulation
Ball manipulations are a widely studied class of manipulations in the literature, where agents can modify their feature vector within a bounded radius ball.
A Theory of PAC Learnability under Transformation Invariances
One interesting observation is that distinguishing between the original data and the transformed data is necessary to achieve optimal accuracy in setting (ii) and (iii), which implies that any algorithm not differentiating between the original and transformed data (including data augmentation) is not optimal.
Accurately Solving Rod Dynamics with Graph Learning
In this contribution, we introduce a novel method to accelerate iterative solvers for rod dynamics with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations.
One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning
In recent years, federated learning has been embraced as an approach for bringing about collaboration across large populations of learning agents.
Robust learning under clean-label attack
We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to fool the algorithm into making mistakes on specific test instances at test time.
Online Learning with Primary and Secondary Losses
On the positive side, we show that running any switching-limited algorithm can achieve this goal if all experts satisfy the assumption that the secondary loss does not exceed the linear threshold by $o(T)$ for any time interval.
Stochastic Bandits with Vector Losses: Minimizing $\ell^\infty$-Norm of Relative Losses
We study two goals: (a) finding the arm with the minimum $\ell^\infty$-norm of relative losses with a given confidence level (which refers to fixed-confidence best-arm identification); (b) minimizing the $\ell^\infty$-norm of cumulative relative losses (which refers to regret minimization).
Structure Adaptive Algorithms for Stochastic Bandits
We study reward maximisation in a wide class of structured stochastic multi-armed bandit problems, where the mean rewards of arms satisfy some given structural constraints, e. g. linear, unimodal, sparse, etc.
Accurately Solving Physical Systems with Graph Learning
In this contribution, we introduce a novel method to accelerate iterative solvers for physical systems with graph networks (GNs) by predicting the initial guesses to reduce the number of iterations.
Almost Optimal Algorithms for Linear Stochastic Bandits with Heavy-Tailed Payoffs
In this paper, under a weaker assumption on noises, we study the problem of \underline{lin}ear stochastic {\underline b}andits with h{\underline e}avy-{\underline t}ailed payoffs (LinBET), where the distributions have finite moments of order $1+\epsilon$, for some $\epsilon\in (0, 1]$.
