333 citations · 941 across the 18 of their papers we have counts for
21 papers
Distributional Off-Policy Evaluation for Slate Recommendations
Shreyas Chaudhari, David Arbour, Georgios Theocharous +1
Recommendation strategies are typically evaluated by using previously logged data, employing off-policy evaluation methods to estimate their expected performance. However, for stra…
FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback
Ashish Singh, Ashutosh Singh, Prateek Agarwal +10
Captions are crucial for understanding scientific visualizations and documents. Existing captioning methods for scientific figures rely on figure-caption pairs extracted from docum…
Local Policy Improvement for Recommender Systems
Dawen Liang, Nikos Vlassis
Recommender systems predict what items a user will interact with next, based on their past interactions. The problem is often approached through supervised learning, but recent adv…
Control Variates for Slate Off-Policy Evaluation
Nikos Vlassis, Ashok Chandrashekar, Fernando Amat Gil +1
We study the problem of off-policy evaluation from batched contextual bandit data with multidimensional actions, often termed slates. The problem is common to recommender systems a…
Sequential causal inference in a single world of connected units
Aurelien Bibaut, Maya Petersen, Nikos Vlassis +2
We consider adaptive designs for a trial involving N individuals that we follow along T time steps. We allow for the variables of one individual to depend on its past and on the pa…
Off-Policy Evaluation of Slate Policies under Bayes Risk
Nikos Vlassis, Fernando Amat Gil, Ashok Chandrashekar
We study the problem of off-policy evaluation for slate bandits, for the typical case in which the logging policy factorizes over the slots of the slate. We slightly depart from th…
On Proximal Causal Learning with Many Hidden Confounders
Nikos Vlassis, Phil Hebda, Stephan McBride +1
We generalize the proximal g-formula of Miao, Geng, and Tchetgen Tchetgen (2018) for causal inference under unobserved confounding using proxy variables. Specifically, we show that…
More Efficient Off-Policy Evaluation through Regularized Targeted Learning
Aurélien F. Bibaut, Ivana Malenica, Nikos Vlassis +1
We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have…
Optimizing over a Restricted Policy Class in Markov Decision Processes
Ershad Banijamali, Yasin Abbasi-Yadkori, Mohammad Ghavamzadeh +1
We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem…
Posterior Sampling for Large Scale Reinforcement Learning
Georgios Theocharous, Zheng Wen, Yasin Abbasi-Yadkori +1
We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algor…
Does Weather Matter? Causal Analysis of TV Logs
Shi Zong, Branislav Kveton, Shlomo Berkovsky +3
Weather affects our mood and behaviors, and many aspects of our life. When it is sunny, most people become happier; but when it rains, some people get depressed. Despite this evide…
Approximate Joint Matrix Triangularization
Nicolo Colombo, Nikos Vlassis
We consider the problem of approximate joint triangularization of a set of noisy jointly diagonalizable real matrices. Approximate joint triangularizers are commonly used in the es…
Stochastic Control via Entropy Compression
Dimitris Achlioptas, Fotis Iliopoulos, Nikos Vlassis
We consider an agent trying to bring a system to an acceptable state by repeated probabilistic action. Several recent works on algorithmizations of the Lovasz Local Lemma (LLL) can…
Conditions for duality between fluxes and concentrations in biochemical networks
Ronan M. T. Fleming, Nikos Vlassis, Ines Thiele +1
Mathematical and computational modelling of biochemical networks is often done in terms of either the concentrations of molecular species or the fluxes of biochemical reactions. Wh…
Spectral Sequence Motif Discovery
Nicolò Colombo, Nikos Vlassis
Sequence discovery tools play a central role in several fields of computational biology. In the framework of Transcription Factor binding studies, motif finding algorithms of incre…
Polytopic uncertainty for linear systems: New and old complexity results
Nikos Vlassis, Raphaël Jungers
We survey the problem of deciding the stability or stabilizability of uncertain linear systems whose region of uncertainty is a polytope. This natural setting has applications in m…
Fast Reconstruction of Compact Context-Specific Metabolic Network Models
Nikos Vlassis, Maria Pires Pacheco, Thomas Sauter
Systemic approaches to the study of a biological cell or tissue rely increasingly on the use of context-specific metabolic network models. The reconstruction of such a model from h…
NP-hardness of polytope M-matrix testing and related problems
Nikos Vlassis
In this note we prove NP-hardness of the following problem: Given a set of matrices, is there a convex combination of those that is a nonsingular M-matrix? Via known characterizati…
Optimal and Approximate Q-value Functions for Decentralized POMDPs
Frans A. Oliehoek, Matthijs T. J. Spaan, Nikos Vlassis
Decision-theoretic planning is a popular approach to sequential decision making problems, because it treats uncertainty in sensing and acting in a principled way. In single-agent f…
Perseus: Randomized Point-based Value Iteration for POMDPs
M. T. J. Spaan, N. Vlassis
Partially observable Markov decision processes (POMDPs) form an attractive and principled framework for agent planning under uncertainty. Point-based approximate techniques for POM…
On the Computational Complexity of Stochastic Controller Optimization in POMDPs
Nikos Vlassis, Michael L. Littman, David Barber
We show that the problem of finding an optimal stochastic 'blind' controller in a Markov decision process is an NP-hard problem. The corresponding decision problem is NP-hard, in P…