11 papers
Capacity-Constrained Online Convex Optimization with Delayed Feedback
Alexander Ryabchenko, Idan Attias, Daniel M. Roy
Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives. In practice, tracking resources are finite, and…
Detoxifying LLMs via Representation Erasure-Based Preference Optimization
Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle +3
Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and simila…
A Reduction from Delayed to Immediate Feedback for Online Convex Optimization with Improved Guarantees
Alexander Ryabchenko, Idan Attias, Daniel M. Roy
We develop a reduction-based framework for online learning with delayed feedback that recovers and improves upon existing results for both first-order and bandit convex optimizatio…
Leveraging Per-Instance Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik +5
We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearn…
Capacity-Constrained Online Learning with Delays: Scheduling Frameworks and Regret Trade-offs
Alexander Ryabchenko, Idan Attias, Daniel M. Roy
We study online learning with oblivious losses and delays under a novel ``capacity constraint'' that limits how many past rounds can be tracked simultaneously for delayed feedback.…
On Traceability in Stochastic Convex Optimization
Sasha Voitovych, Mahdi Haghifam, Idan Attias +3
In this paper, we investigate the necessity of traceability for accurate learning in stochastic convex optimization (SCO) under geometries. Informally, we say a learning a…
The Non-Local Model Merging Problem: Permutation Symmetries and Variance Collapse
Ekansh Sharma, Daniel M. Roy, Gintare Karolina Dziugaite
Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all…
Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Ziyi Liu, Idan Attias, Daniel M. Roy
We study the fundamental problem of sequential probability assignment, also known as online learning with logarithmic loss, with respect to an arbitrary, possibly nonparametric hyp…
Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals
Ziyi Liu, Idan Attias, Daniel M. Roy
In this work, we investigate the problem of adapting to the presence or absence of causal structure in multi-armed bandit problems. In addition to the usual reward signal, we assum…
Simultaneous linear connectivity of neural networks modulo permutation
Ekansh Sharma, Devin Kwok, Tom Denton +3
Neural networks typically exhibit permutation symmetries which contribute to the non-convexity of the networks' loss landscapes, since linearly interpolating between two permuted v…
Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization
Idan Attias, Gintare Karolina Dziugaite, Mahdi Haghifam +2
In this work, we investigate the interplay between memorization and learning in the context of \emph{stochastic convex optimization} (SCO). We define memorization via the informati…