2021-12
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity
NEURIPS 2021
(2021-12-06)
proceedings.neurips.ccPDF[Also on arXiv preprint arXiv:2107.00052 (2021-06-30)]2021-09
Predicting Tactical Solutions to Operational Planning Problems Under Imperfect Information
Informs Journal on Computing
(2021-09-21)
pubsonline.informs.org[Also on arXiv preprint arXiv:1901.07935 (2018-07-31)]2021-07
Discovering Latent Causal Variables via Mechanism Sparsity: A New Principle for Nonlinear ICA
Structured Convolutional Kernel Networks for Airline Crew Scheduling
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets
2021-05
Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search)
Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning
2021-03
Implicit Regularization via Neural Feature Alignment
AISTATS 2021
(2021-03-18)
proceedings.mlr.pressPDF[Also on arXiv preprint arXiv:2008.00938 (2020-08-03)]Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
AISTATS 2021
(2021-03-18)
proceedings.mlr.pressPDF[Also on arXiv preprint arXiv:2002.10542 (2020-02-24)]Online Adversarial Attacks.
2021-02
SVRG Meets AdaGrad: Painless Variance Reduction.
2020-12
Machine Learning in Airline Crew Pairing to Construct Initial Clusters for Dynamic Constraint Aggregation
EURO Journal on Transportation and Logistics
(2020-12-01)
www.sciencedirect.com[Also on arXiv preprint arXiv:2010.00134 (2020-09-30)][Also on Les Cahiers du GERAD (2020-02-01)]2020-11
Geometry-Aware Universal Mirror-Prox.
On the Convergence of Continuous Constrained Optimization for Structure Learning.
2020-09
Flight-connection Prediction for Airline Crew Scheduling to Construct Initial Clusters for OR Optimizer
2020-08
Implicit Regularization in Deep Learning: A View from Function Space.
2020-07
Stochastic Hamiltonian Gradient Methods for Smooth Games
Differentiable Causal Discovery from Interventional Data
Adversarial Example Games.
2020-06
To Each Optimizer a Norm, To Each Norm its Generalization.
GAIT: A Geometric Approach to Information Theory
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Differentiable Games.
Accelerating Smooth Games by Manipulating Spectral Shapes.
AISTATS 2020
(2020-06-03)
proceedings.mlr.pressPDF[Also on arXiv preprint arXiv:2001.00602 (2020-01-02)]Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation.
AISTATS 2020
(2020-06-03)
proceedings.mlr.pressPDF[Also on arXiv preprint arXiv:1910.04920 (2019-10-11)]2020-05
An Analysis of the Adaptation Speed of Causal Models
An Analysis of the Adaptation Speed of Causal Models
2020-04
Gradient-Based Neural DAG Learning
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
2020-01
Adversarial Example Games
2019-09
Are Few-shot Learning Benchmarks Too Simple ?
Scattering Networks for Hybrid Representation Learning
2019-06
GEAR: Geometry-Aware Rényi Information.
GAIT: A Geometric Approach to Information Theory
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games
A Tight and Unified Analysis of Extragradient for a Whole Spectrum of Differentiable Games.
2019-05
Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates
2019-04
Negative Momentum for Improved Game Dynamics
Flight-connection prediction for airline crew scheduling to construct initial clusters for OR optimizer
2019-02
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
Centroid Networks for Few-Shot Clustering and Unsupervised Few-Shot Classification.
2019-01
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks
Reducing Noise in GAN Training with Variance Reduced Extragradient
2018-10
A Modern Take on the Bias-Variance Tradeoff in Neural Networks
Quantifying Learning Guarantees for Convex but Inconsistent Surrogates
2018-09
Learning from Narrated Instruction Videos
2018-08
2018-07
Predicting Solution Summaries to Integer Linear Programs under Imperfect Information with Machine Learning.
Negative Momentum for Improved Game Dynamics
2018-03
Frank-Wolfe Splitting via Augmented Lagrangian Method
AISTATS 2018
(2018-03-31)
proceedings.mlr.pressPDF[LATEST on arXiv: Optimization and Control (2018-04-09)]2018-02
A Variational Inequality Perspective on Generative Adversarial Networks
SeaRNN: Training RNNs with Global-Local Losses
Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
2018-01
A3T: Adversarially Augmented Adversarial Training.
Improved asynchronous parallel optimization analysis for stochastic incremental methods
Journal of Machine Learning Research
(2018-01-01)
jmlr.orgPDF[LATEST on arXiv preprint arXiv:1801.03749 (2018-01-11)]Publications collected and formatted using Paperoni