78 citations · 677 across the 85 of their papers we have counts for
106 papers
On the LLM Verification for Argument Graph Generation
Jakub Bąba, Jarosław A. Chudziak
Multi-agent LLM systems can formalize natural-language argumentation end-to-end, turning plain text into structured graphs by classifying components, connecting them with relations…
Learning to Price with Persuasion
Maria-Florina Balcan, Tejas Pagare, Karan Singh
Motivated by modern marketplaces, where the platform or the seller routinely gathers detailed user profiles, we study a novel learning theoretic model that simultaneously involves…
Efficient Online Proportional Sampling with Applications to Smoothed Online Learning
Amirmahdi Mirfakhar, Maria-Florina Balcan, Hedyeh Beyhaghi
We study the problem of efficient online proportional sampling from a high-dimensional domain under a -smoothed adversary, where the sampling distribution is induced by a dynami…
Reward Learning from Best-of- Preference Data: Targets, Tradeoffs, and Design Principles
Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar
Best-of- sampling is widely used to construct pairwise preference data: candidates are drawn from a base distribution, and the best is paired with a rejected response. Despi…
Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought Verification
Maria-Florina Balcan, Avrim Blum, Kiriaki Fragkia +2
Large Language Models (LLMs) using chain-of-thought have demonstrated great potential for solving complex reasoning and planning tasks. Despite these advances, LLM-generated output…
The Complexity of Proper Equilibrium in Extensive-Form and Polytope Games
Brian Hu Zhang, Ioannis Anagnostides, Kiriaki Fragkia +2
The proper equilibrium, introduced by Myerson (1978), is a classic refinement of the Nash equilibrium that has been referred to as the "mother of all refinements." For normal-form…
What Does Preference Learning Recover from Pairwise Comparison Data?
Rattana Pukdee, Maria-Florina Balcan, Pradeep Ravikumar
Pairwise preference learning is central to machine learning, with recent applications in aligning language models with human preferences. A typical dataset consists of triplets $(x…
The Active and Noise-Tolerant Strategic Perceptron
Maria-Florina Balcan, Hedyeh Beyhaghi
We initiate the study of active learning algorithms for classifying strategic agents. Active learning is a well-established framework in machine learning in which the learner selec…
The Complexity of Equilibrium Refinements in Potential Games
Ioannis Anagnostides, Maria-Florina Balcan, Kiriaki Fragkia +3
The complexity of computing equilibrium refinements has been at the forefront of algorithmic game theory research, but it has remained open in the seminal class of potential games;…
Distribution-dependent Generalization Bounds for Tuning Linear Regression Across Tasks
Maria-Florina Balcan, Saumya Goyal, Dravyansh Sharma
Modern regression problems often involve high-dimensional data and a careful tuning of the regularization hyperparameters is crucial to avoid overly complex models that may overfit…
Revenue-Optimal Efficient Mechanism Design with General Type Spaces
Siddharth Prasad, Maria-Florina Balcan, Tuomas Sandholm
We derive the revenue-optimal efficient (welfare-maximizing) mechanism in a general multidimensional mechanism design setting when type spaces -- that is, the underlying domains fr…
Weakest Bidder Types and New Core-Selecting Combinatorial Auctions
Siddharth Prasad, Maria-Florina Balcan, Tuomas Sandholm
Core-selecting combinatorial auctions are popular auction designs that constrain prices to eliminate the incentive for any group of bidders -- with the seller -- to renegotiate for…
On Learning Verifiers and Implications to Chain-of-Thought Reasoning
Maria-Florina Balcan, Avrim Blum, Zhiyuan Li +1
Chain-of-Thought reasoning has emerged as a powerful approach for solving complex mathematical and logical problems. However, it can often veer off track through incorrect or unsub…
Learning in Structured Stackelberg Games
Maria-Florina Balcan, Kiriaki Fragkia, Keegan Harris
We initiate the study of structured Stackelberg games, a novel form of strategic interaction between a leader and a follower where contextual information can be predictive of the f…
Nearly-Optimal Bandit Learning in Stackelberg Games with Side Information
Maria-Florina Balcan, Martino Bernasconi, Matteo Castiglioni +3
We study the problem of online learning in Stackelberg games with side information between a leader and a sequence of followers. In every round the leader observes contextual infor…
Sample complexity of data-driven tuning of model hyperparameters in neural networks with structured parameter-dependent dual function
Maria-Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma
Modern machine learning algorithms, especially deep learning based techniques, typically involve careful hyperparameter tuning to achieve the best performance. Despite the surge of…
Subsidy design for better social outcomes
Maria-Florina Balcan, Matteo Pozzi, Dravyansh Sharma
Overcoming the impact of selfish behavior of rational players in multiagent systems is a fundamental problem in game theory. Without any intervention from a central agent, strategi…
Algorithm Configuration for Structured Pfaffian Settings
Maria-Florina Balcan, Anh Tuan Nguyen, Dravyansh Sharma
Data-driven algorithm design automatically adapts algorithms to specific application domains, achieving better performance. In the context of parameterized algorithms, this approac…
Learning accurate and interpretable tree-based models
Maria-Florina Balcan, Dravyansh Sharma
Decision trees and their ensembles are popular in machine learning as easy-to-understand models. Several techniques have been proposed in the literature for learning tree-based cla…
Regret Minimization in Stackelberg Games with Side Information
Keegan Harris, Zhiwei Steven Wu, Maria-Florina Balcan
Algorithms for playing in Stackelberg games have been deployed in real-world domains including airport security, anti-poaching efforts, and cyber-crime prevention. However, these a…
Spectrally Transformed Kernel Regression
Runtian Zhai, Rattana Pukdee, Roger Jin +2
Unlabeled data is a key component of modern machine learning. In general, the role of unlabeled data is to impose a form of smoothness, usually from the similarity information enco…
New Sequence-Independent Lifting Techniques for Cutting Planes and When They Induce Facets
Siddharth Prasad, Ellen Vitercik, Maria-Florina Balcan +1
Sequence-independent lifting is a procedure for strengthening valid inequalities of an integer program. We generalize the sequence-independent lifting method of Gu, Nemhauser, and…
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Mikhail Khodak, Edmond Chow, Maria-Florina Balcan +1
Solving a linear system is a fundamental scientific computing primitive for which numerous solvers and preconditioners have been developed. These come with parameters whose…
Meta-Learning Adversarial Bandit Algorithms
Mikhail Khodak, Ilya Osadchiy, Keegan Harris +4
We study online meta-learning with bandit feedback, with the goal of improving performance across multiple tasks if they are similar according to some natural similarity measure. A…