114 citations · 379 across the 34 of their papers we have counts for
37 papers
To Believe or Not to Believe Your LLM
Yasin Abbasi Yadkori, Ilja Kuzborskij, András György +1
We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider bo…
Mitigating LLM Hallucinations via Conformal Abstention
Yasin Abbasi Yadkori, Ilja Kuzborskij, David Stutz +9
We develop a principled procedure for determining when a large language model (LLM) should abstain from responding (e.g., by saying "I don't know") in a general domain, instead of…
Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
Qinghua Liu, Gellért Weisz, András György +2
While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy opti…
A Second-Order Method for Stochastic Bandit Convex Optimisation
Tor Lattimore, András György
We introduce a simple and efficient algorithm for unconstrained zeroth-order stochastic convex bandits and prove its regret is at most $(1 + r/d)[d^{1.5} \sqrt{n} + d^3] polylog(n,…
A New Look at Dynamic Regret for Non-Stationary Stochastic Bandits
Yasin Abbasi-Yadkori, Andras Gyorgy, Nevena Lazic
We study the non-stationary stochastic multi-armed bandit problem, where the reward statistics of each arm may change several times during the course of learning. The performance o…
Learning to Minimize Age of Information over an Unreliable Channel with Energy Harvesting
Elif Tugce Ceran, Deniz Gunduz, Andras Gyorgy
The time average expected age of information (AoI) is studied for status updates sent over an error-prone channel from an energy-harvesting transmitter with a finite-capacity batte…
A Reinforcement Learning Approach to Age of Information in Multi-User Networks with HARQ
Elif Tugce Ceran, Deniz Gunduz, Andras Gyorgy
Scheduling the transmission of time-sensitive information from a source node to multiple users over error-prone communication channels is studied with the goal of minimizing the lo…
Mutual Information Constraints for Monte-Carlo Objectives
Gábor Melis, András György, Phil Blunsom
A common failure mode of density models trained as variational autoencoders is to model the data without relying on their latent variables, rendering these variables useless. Two c…
Adapting to Delays and Data in Adversarial Multi-Armed Bandits
András György, Pooria Joulani
We consider the adversarial multi-armed bandit problem under delayed feedback. We analyze variants of the Exp3 algorithm that tune their step-size using only information (about the…
Mirror Descent and the Information Ratio
Tor Lattimore, András György
We establish a connection between the stability of mirror descent and the information ratio by Russo and Van Roy [2014]. Our analysis shows that mirror descent with suitable loss e…
Minimal Assumptions Refinement for GR(1) Specifications
Davide G. Cavezza, Dalal Alrajeh, Andras Gyorgy
Reactive synthesis is concerned with finding a correct-by-construction controller from formal specifications, typically expressed in Linear Temporal Logic (LTL). The specifications…
Meta-learning of Sequential Strategies
Pedro A. Ortega, Jane X. Wang, Mark Rowland +21
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. O…
Detecting Overfitting via Adversarial Examples
Roman Werpachowski, András György, Csaba Szepesvári
The repeated community-wide reuse of test sets in popular benchmark problems raises doubts about the credibility of reported test-error rates. Verifying whether a learned model is…
The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation Detection
Muhammad Zaid Hameed, Andras Gyorgy, Deniz Gunduz
We consider a communication scenario, in which an intruder tries to determine the modulation scheme of the intercepted signal. Our aim is to minimize the accuracy of the intruder,…
Reinforcement Learning to Minimize Age of Information with an Energy Harvesting Sensor with HARQ and Sensing Cost
Elif Tuğçe Ceran, Deniz Gündüz, András György
The time average expected age of information (AoI) is studied for status updates sent from an energy-harvesting transmitter with a finite-capacity battery. The optimal scheduling p…
LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration
Gellért Weisz, András György, Csaba Szepesvári
We consider the problem of configuring general-purpose solvers to run efficiently on problem instances drawn from an unknown distribution. The goal of the configurator is to find a…
Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems
Timothy A. Mann, Sven Gowal, András György +4
Predicting delayed outcomes is an important problem in recommender systems (e.g., if customers will finish reading an ebook). We formalize the problem as an adversarial, delayed on…
Adaptive MCMC via Combining Local Samplers
Kiarash Shaloudegi, András György
Markov chain Monte Carlo (MCMC) methods are widely used in machine learning. One of the major problems with MCMC is the question of how to design chains that mix fast over the whol…
A Reinforcement Learning Approach to Age of Information in Multi-User Networks
Elif Tuğçe Ceran, Deniz Gündüz, András György
Scheduling the transmission of time-sensitive data to multiple users over error-prone communication channels is studied with the goal of minimizing the long-term average age of inf…
A Weakness Measure for GR(1) Formulae
Davide G. Cavezza, Dalal Alrajeh, András György
In spite of the theoretical and algorithmic developments for system synthesis in recent years, little effort has been dedicated to quantifying the quality of the specifications use…
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
Andrea Paudice, Luis Muñoz-González, Andras Gyorgy +1
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among other…
A Reinforcement-Learning Approach to Proactive Caching in Wireless Networks
Samuel O. Somuyiwa, Andras Gyorgy, Deniz Gunduz
We consider a mobile user accessing contents in a dynamic environment, where new contents are generated over time (by the user's contacts), and remain relevant to the user for rand…
Average Age of Information with Hybrid ARQ under a Resource Constraint
Elif Tugce Ceran, Deniz Gunduz, Andras Gyorgy
Scheduling of the transmission of status updates over an error-prone communication channel is studied in order to minimize the long-term average age of information (AoI) at the des…
A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds
Pooria Joulani, András György, Csaba Szepesvári
Recently, much work has been done on extending the scope of online learning and incremental stochastic optimization algorithms. In this paper we contribute to this effort in two wa…