1 citations · 1 across the 4 of their papers we have counts for
9 papers · 1 filter
Regularized Large Neighborhood Search
Germain Vivier-Ardisson, Laurent Demonet, Axel Parmentier +1
Operations research practitioners typically tackle NP-hard combinatorial problems using large neighborhood search (LNS), a scalable heuristic that iteratively refines a current sol…
Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction
Mathieu Blondel, Michael E. Sander, Germain Vivier-Ardisson +2
Autoregressive models (ARMs) currently constitute the dominant paradigm for large language models (LLMs). Energy-based models (EBMs) represent another class of models, which have h…
Differentiable Knapsack and Top-k Operators via Dynamic Programming
Germain Vivier-Ardisson, Michaël E. Sander, Axel Parmentier +1
Knapsack and Top-k operators are useful for selecting discrete subsets of variables. However, their integration into neural networks is challenging as they are piecewise constant,…
Learning with Local Search MCMC Layers
Germain Vivier-Ardisson, Mathieu Blondel, Axel Parmentier
Integrating combinatorial optimization layers into neural networks has recently attracted significant research interest. However, many existing approaches lack theoretical guarante…
Joint Learning of Energy-based Models and their Partition Function
Michael E. Sander, Vincent Roulet, Tianlin Liu +1
Energy-based models (EBMs) offer a flexible framework for parameterizing probability distributions using neural networks. However, learning EBMs by exact maximum likelihood estimat…
Loss Functions and Operators Generated by f-Divergences
Vincent Roulet, Tianlin Liu, Nino Vieillard +2
The logistic loss (a.k.a. cross-entropy loss) is one of the most popular loss functions used for multiclass classification. It is also the loss function of choice for next-token pr…