activity
20242026
collaborators

11 papers

cs.LG2026

When Clean Data Hurts: Learning with Monotone Corruptions Beyond Binary Classification

Julian Asilis, Shaddin Dughmi, Chirag Pabbaraju

Optimal learners are tailored to exploit the i.i.d.\ data assumption underlying the classic PAC model. What if an i.i.d.\ training sample were corrupted with correctly labeled exam…

cs.LG2025

On Agnostic PAC Learning in the Small Error Regime

Julian Asilis, Mikael Møller Høgsgaard, Grigoris Velegkas

Binary classification in the classic PAC model exhibits a curious phenomenon: Empirical Risk Minimization (ERM) learners are suboptimal in the realizable case yet optimal in the ag…

cs.LG2025

Proper Learnability and the Role of Unlabeled Data

Julian Asilis, Siddartha Devic, Shaddin Dughmi +2

Proper learning refers to the setting in which learners must emit predictors in the underlying hypothesis class , and often leads to learners with simple algorithmic forms (e.g.…

cs.DM2025

Semi-Random Graphs, Robust Asymmetry, and Reconstruction

Julian Asilis, Xi Chen, Dutch Hansen +1

The Graph Reconstruction Conjecture famously posits that any undirected graph on at least three vertices is determined up to isomorphism by its family of (unlabeled) induced subgra…

cs.LG2025

Understanding Aggregations of Proper Learners in Multiclass Classification

Julian Asilis, Mikael Møller Høgsgaard, Grigoris Velegkas

Multiclass learnability is known to exhibit a properness barrier: there are learnable classes which cannot be learned by any proper learner. Binary classification faces no such bar…

cs.CL2025

Resa: Transparent Reasoning Models via SAEs

Shangshang Wang, Julian Asilis, Ömer Faruk Akgül +4

How cost-effectively can we elicit strong reasoning in language models by leveraging their underlying representations? We answer this question with Resa, a family of 1.5B reasoning…