activity
20232026
most citedRepeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

7 citations · 7 across the 15 of their papers we have counts for

collaborators

20 papers

cs.LG2026

Constrained Learning with Universally Learnable Concept Classes

Herlock SeyedAbolfazl Rahimi, Spyridon Pougkakiotis, Dionysis Kalogerias

We study constrained statistical learning over infinite-dimensional hypothesis classes in the fully nonconvex setting, and establish universal PACC learnability of the solutions of…

cs.CL2026

Self-Improving In-Context Learning

Baturay Saglam, Dionysis Kalogerias

We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is that the log-probabilities a…

cs.CL2026

Test-Time Safety Alignment

Baturay Saglam, Dionysis Kalogerias

Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. Howeve…

math.OC2026

Risk-Aware Linear-Quadratic Regulation with Temporally Coupled States

Chuanning Wei, Kin Fung Li, Dionysis Kalogerias +1

We formulate and solve a discrete-time linear-quadratic regulation (LQR) problem in a finite horizon that penalizes temporal variability and stochastic variability of the state tra…

cs.CL2026

Test-Time Detoxification without Training or Learning Anything

Baturay Saglam, Dionysis Kalogerias

Large language models can produce toxic or inappropriate text even for benign inputs, creating risks when deployed at scale. Detoxification is therefore important for safety and us…

cs.LG2025

Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents

Jane H. Lee, Baturay Saglam, Spyridon Pougkakiotis +2

Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constrai…