 Storchastic: A Framework for General Stochastic Automatic
DifferentiationNeural Information Processing Systems (NeurIPS), 2021 |
 Neuro-algorithmic Policies enable Fast Combinatorial GeneralizationInternational Conference on Machine Learning (ICML), 2021 |
 Learning Binary Decision Trees by Argmin DifferentiationInternational Conference on Machine Learning (ICML), 2020 |
 Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent
Structure LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2020 |
 Learning Randomly Perturbed Structured Predictors for Direct Loss
MinimizationInternational Conference on Machine Learning (ICML), 2020 |
 Understanding Deep Architectures with Reasoning LayerNeural Information Processing Systems (NeurIPS), 2020 |
 Gradient Estimation with Stochastic Softmax TricksNeural Information Processing Systems (NeurIPS), 2020 |
 Proximal Mapping for Deep RegularizationNeural Information Processing Systems (NeurIPS), 2020 |
 Rationalizing Text Matching: Learning Sparse Alignments via Optimal
TransportAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Generalized Entropy Regularization or: There's Nothing Special about
Label SmoothingAnnual Meeting of the Association for Computational Linguistics (ACL), 2020 |
 Deep Graph Matching via Blackbox Differentiation of Combinatorial
SolversEuropean Conference on Computer Vision (ECCV), 2020 |
 Fast Differentiable Sorting and RankingInternational Conference on Machine Learning (ICML), 2020 |
 LP-SparseMAP: Differentiable Relaxed Optimization for Sparse Structured
PredictionInternational Conference on Machine Learning (ICML), 2020 Vlad Niculae André F. T. Martins |
 Not All Attention Is Needed: Gated Attention Network for Sequence DataAAAI Conference on Artificial Intelligence (AAAI), 2019 |
 Graph Structured Prediction Energy NetworksNeural Information Processing Systems (NeurIPS), 2019 |
 Structured Prediction with Projection OraclesNeural Information Processing Systems (NeurIPS), 2019 |
 Neural Oblivious Decision Ensembles for Deep Learning on Tabular DataInternational Conference on Learning Representations (ICLR), 2019 |
 Deep Equilibrium ModelsNeural Information Processing Systems (NeurIPS), 2019 |
 |
 |
 Augmenting Neural Networks with First-order LogicAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 Sparse Sequence-to-Sequence ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2019 |
 A Smoother Way to Train Structured Prediction ModelsNeural Information Processing Systems (NeurIPS), 2019 |
 |
 Structured Attention NetworksInternational Conference on Learning Representations (ICLR), 2017 |
