Simon Lacoste-Julien

Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies JMLR 2026 Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalization UAI 2026 Accelerating Training with Neuron Interaction and Nowcasting Networks ICLR 2025 Feasible Learning AISTATS 2025 Performative Prediction on Games and Mechanism Design AISTATS 2025 Balancing Act: Constraining Disparate Impact in Sparse Models ICLR 2024 On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization ICML 2024 On the Identifiability of Quantized Factors CLeaR 2024 Weight-Sharing Regularization AISTATS 2024 Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation NeurIPS 2023 Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models? ICML 2023 CrossSplit: Mitigating Label Noise Memorization through Data Splitting ICML 2023 Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning ICML 2023 Unlocking Slot Attention by Changing Optimal Transport Costs ICML 2023 Bayesian structure learning with generative flow networks UAI 2022 Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints NeurIPS 2022 Data-Efficient Structured Pruning via Submodular Optimization NeurIPS 2022 Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA CLeaR 2022 Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution NeurIPS 2022 Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation ICLR 2022 Online Adversarial Attacks ICLR 2022 On the Convergence of Continuous Constrained Optimization for Structure Learning AISTATS 2022 Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets ICML 2021 An Analysis of the Adaptation Speed of Causal Models AISTATS 2021 Implicit Regularization via Neural Feature Alignment AISTATS 2021 Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning ICLR 2021 Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity NeurIPS 2021 Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence AISTATS 2021 Structured Convolutional Kernel Networks for Airline Crew Scheduling ICML 2021 Accelerating Smooth Games by Manipulating Spectral Shapes AISTATS 2020 A Closer Look at the Optimization Landscapes of Generative Adversarial Networks ICLR 2020 Adversarial Example Games NeurIPS 2020 A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games AISTATS 2020 Differentiable Causal Discovery from Interventional Data NeurIPS 2020 Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation AISTATS 2020 GAIT: A Geometric Approach to Information Theory AISTATS 2020 Gradient-Based Neural DAG Learning ICLR 2020 Stochastic Hamiltonian Gradient Methods for Smooth Games ICML 2020 A Variational Inequality Perspective on Generative Adversarial Networks ICLR 2019 Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks NeurIPS 2019 Negative Momentum for Improved Game Dynamics AISTATS 2019 Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates NeurIPS 2019 Reducing Noise in GAN Training with Variance Reduced Extragradient NeurIPS 2019 Frank-Wolfe Splitting via Augmented Lagrangian Method AISTATS 2018 Improved Asynchronous Parallel Optimization Analysis for Stochastic Incremental Methods JMLR 2018 Quantifying Learning Guarantees for Convex but Inconsistent Surrogates NeurIPS 2018 SEARNN: Training RNNs with global-local losses ICLR 2018 A Closer Look at Memorization in Deep Networks ICML 2017 ASAGA: Asynchronous Parallel SAGA AISTATS 2017 Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization NeurIPS 2017 Frank-Wolfe Algorithms for Saddle Point Problems AISTATS 2017 Joint Discovery of Object States and Manipulation Actions ICCV 2017 On Structured Prediction Theory with Calibrated Convex Surrogate Losses NeurIPS 2017 Beyond CCA: Moment Matching for Multi-View Models ICML 2016 Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs ICML 2016 PAC-Bayesian Theory Meets Bayesian Inference NeurIPS 2016 Unsupervised Learning From Narrated Instruction Videos CVPR 2016 Barrier Frank-Wolfe for Marginal Inference NeurIPS 2015 On Pairwise Costs for Network Flow Multi-Object Tracking CVPR 2015 On the Global Linear Convergence of Frank-Wolfe Optimization Variants NeurIPS 2015 Rethinking LDA: Moment Matching for Discrete ICA NeurIPS 2015 Sequential Kernel Herding: Frank-Wolfe Optimization for Particle Filtering AISTATS 2015 Variance Reduced Stochastic Gradient Descent with Neighbors NeurIPS 2015 SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives NeurIPS 2014 Block-Coordinate Frank-Wolfe Optimization for Structural SVMs ICML 2013 DiscLDA: Discriminative Learning for Dimensionality Reduction and Classification NeurIPS 2008 Structured Prediction, Dual Extragradient and Bregman Projections JMLR 2006 Word Alignment via Quadratic Assignment NAACL 2006 A Discriminative Matching Approach to Word Alignment EMNLP 2005