249 citations · 348 across the 19 of their papers we have counts for
25 papers
Climbing the Design Ladder: Sequential Knowledge Distillation for Early-Stage Circuit Timing Prediction
Reza Moravej, Fahad Rahman Amik, Zhanguang Zhang +2
Integrated circuit design involves multiple design stages: logic synthesis, floorplanning, placement, and routing, with each stage taking hours to weeks to complete. Discovering ti…
Abductive Reasoning with Probabilistic Commonsense
Joseph Cotnareanu, Chiara Roverato, Han Zhou +3
Recent efforts to improve the reasoning abilities of Large Language Models (LLMs) have focused on integrating formal logic solvers within neurosymbolic frameworks. A key challenge…
One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
Chris Cameron, Wangzheng Wang, Nikita Ivanov +3
Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where e…
A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
Joseph Cotnareanu, Didier Chetelat, Yingxue Zhang +1
Although Large Language Models (LLMs) have demonstrated impressive formal reasoning abilities, they often break down when problems require complex proof planning. One promising app…
InnerThoughts: Disentangling Representations and Predictions in Large Language Models
Didier Chételat, Joseph Cotnareanu, Rylee Thompson +2
Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the pro…
Refining Answer Distributions for Improved Large Language Model Reasoning
Soumyasundar Pal, Didier Chételat, Yingxue Zhang +1
Large Language Models (LLMs) have exhibited an impressive capability to perform reasoning tasks, especially if they are encouraged to generate a sequence of intermediate steps. Rea…
The Graph's Apprentice: Teaching an LLM Low Level Knowledge for Circuit Quality Estimation
Reza Moravej, Saurabh Bodhe, Zhanguang Zhang +6
Logic synthesis is a crucial phase in the circuit design process, responsible for transforming hardware description language (HDL) designs into optimized netlists. However, traditi…
GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection
Zhanguang Zhang, Didier Chetelat, Joseph Cotnareanu +7
Boolean satisfiability (SAT) problems are routinely solved by SAT solvers in real-life applications, yet solving time can vary drastically between solvers for the same instance. Th…
Exploring the Power of Graph Neural Networks in Solving Linear Optimization Problems
Chendi Qian, Didier Chételat, Christopher Morris
Recently, machine learning, particularly message-passing graph neural networks (MPNNs), has gained traction in enhancing exact optimization algorithms. For example, MPNNs speed up…
Learning to Compare Nodes in Branch and Bound with Graph Neural Networks
Abdel Ghani Labassi, Didier Chételat, Andrea Lodi
Branch-and-bound approaches in integer programming require ordering portions of the space to explore next, a problem known as node comparison. We propose a new siamese graph neural…
Lookback for Learning to Branch
Prateek Gupta, Elias B. Khalil, Didier Chetélat +4
The expressive and computationally inexpensive bipartite Graph Neural Networks (GNN) have been shown to be an important component of deep learning based Mixed-Integer Linear Progra…
Learning to branch with Tree MDPs
Lara Scavuzzo, Feng Yang Chen, Didier Chételat +4
State-of-the-art Mixed Integer Linear Program (MILP) solvers combine systematic tree search with a plethora of hard-coded heuristics, such as the branching rule. The idea of learni…
Continuous cutting plane algorithms in integer programming
Didier Chételat, Andrea Lodi
Cutting planes for mixed-integer linear programs (MILPs) are typically computed in rounds by iteratively solving optimization problems, the so-called separation. Instead, we refram…
The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insights
Maxime Gasse, Quentin Cappart, Jonas Charfreitag +38
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolatio…
Ecole: A Library for Learning Inside MILP Solvers
Antoine Prouvost, Justin Dumouchelle, Maxime Gasse +2
In this paper we describe Ecole (Extensible Combinatorial Optimization Learning Environments), a library to facilitate integration of machine learning in combinatorial optimization…
Combinatorial optimization and reasoning with graph neural networks
Quentin Cappart, Didier Chételat, Elias Khalil +3
Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolatio…
Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers
Antoine Prouvost, Justin Dumouchelle, Lara Scavuzzo +3
We present Ecole, a new library to simplify machine learning research for combinatorial optimization. Ecole exposes several key decision tasks arising in general-purpose combinator…
Change Point Detection by Cross-Entropy Maximization
Aurélien Serre, Didier Chételat, Andrea Lodi
Many offline unsupervised change point detection algorithms rely on minimizing a penalized sum of segment-wise costs. We extend this framework by proposing to minimize a sum of dis…
Exact Combinatorial Optimization with Graph Convolutional Neural Networks
Maxime Gasse, Didier Chételat, Nicola Ferroni +2
Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose a new graph convolutional neural network model for learning branch-and-bound…
The middle-scale asymptotics of Wishart matrices
Didier Chételat, Martin T. Wells
We study the behavior of a real -dimensional Wishart random matrix with degrees of freedom when but . We establish the existence of…
On the Domain of Attraction of a Tracy-Widom Law with Applications to Testing Multiple Largest Roots
Didier Chételat, Rajendran Narayanan, Martin T. Wells
The greatest root statistic arises as the test statistic in several multivariate analysis settings. Suppose there is a global null hypothesis that consists of different independent…
Improved Second Order Estimation in the Singular Multivariate Normal Model
Didier Chételat, Martin T. Wells
We consider the problem of estimating covariance and precision matrices, and their associated discriminant coefficients, from normal data when the rank of the covariance matrix is…
Optimal Two-Step Prediction in Regression
Didier Chételat, Johannes Lederer, Joseph Salmon
High-dimensional prediction typically comprises two steps: variable selection and subsequent least-squares refitting on the selected variables. However, the standard variable selec…
Noise Estimation in the Spiked Covariance Model
Didier Chételat, Martin T. Wells
The problem of estimating a spiked covariance matrix in high dimensions under Frobenius loss, and the parallel problem of estimating the noise in spiked PCA is investigated. We pro…