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