Aurélien Lucchi

Nikita Doikov

CoRR, 2024

Initial Guessing Bias: How Untrained Networks Favor Some Classes.

[BibT_eX]

[DOI]

Emanuele Francazi

Marco Baity-Jesi

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

SDEs for Minimax Optimization.

[BibT_eX]

[DOI]

Enea Monzio Compagnoni

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Regret-Optimal Federated Transfer Learning for Kernel Regression with Applications in American Option Pricing.

[BibT_eX]

[DOI]

CoRR, 2023

A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Theoretical Analysis of the Learning Dynamics under Class Imbalance.

[BibT_eX]

[DOI]

Emanuele Francazi

Marco Baity-Jesi

Proceedings of the International Conference on Machine Learning, 2023

An SDE for Modeling SAM: Theory and Insights.

[BibT_eX]

[DOI]

Enea Monzio Compagnoni

Proceedings of the International Conference on Machine Learning, 2023

Mastering Spatial Graph Prediction of Road Networks.

[BibT_eX]

[DOI]

Sotiris Anagnostidis

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

Characterizing the Effect of Class Imbalance on the Learning Dynamics.

[BibT_eX]

[DOI]

Emanuele Francazi

Marco Baity-Jesi

CoRR, 2022

Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

On the Theoretical Properties of Noise Correlation in Stochastic Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Anticorrelated Noise Injection for Improved Generalization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Phenomenology of Double Descent in Finite-Width Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Generalization Through the Lens of Leave-One-Out Error.

[BibT_eX]

[DOI]

Gregor Bachmann

Proceedings of the Tenth International Conference on Learning Representations, 2022

Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Vanishing Curvature in Randomly Initialized Deep ReLU Networks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

A Globally Convergent Evolutionary Strategy for Stochastic Constrained Optimization with Applications to Reinforcement Learning.

[BibT_eX]

[DOI]

Youssef Diouane

Vihang Prakash Patil

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Variational quantum Boltzmann machines.

[BibT_eX]

[DOI]

Christa Zoufal

Stefan Woerner

Quantum Mach. Intell., 2021

The power of quantum neural networks.

[BibT_eX]

[DOI]

Nat. Comput. Sci., 2021

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks.

[BibT_eX]

[DOI]

Frontiers Artif. Intell., 2021

Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks.

[BibT_eX]

[DOI]

CoRR, 2021

Generative Minimization Networks: Training GANs Without Competition.

[BibT_eX]

[DOI]

CoRR, 2021

On the Second-order Convergence Properties of Random Search Methods.

[BibT_eX]

[DOI]

Giambattista Parascandolo

Adamos Solomou

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Neural Symbolic Regression that scales.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Learning Generative Models of Textured 3D Meshes from Real-World Images.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Direct-Search for a Class of Stochastic Min-Max Problems.

[BibT_eX]

[DOI]

Sotirios-Konstantinos Anagnostidis

Youssef Diouane

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Momentum Improves Optimization on Riemannian Manifolds.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Scalable Graph Networks for Particle Simulations.

[BibT_eX]

[DOI]

Karolis Martinkus

Nathanaël Perraudin

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Theoretical Understanding of Batch-normalization: A Markov Chain Perspective.

[BibT_eX]

[DOI]

CoRR, 2020

Convolutional Generation of Textured 3D Meshes.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Batch normalization provably avoids ranks collapse for randomly initialised deep networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Randomized Block-Diagonal Preconditioning for Parallel Learning.

[BibT_eX]

[DOI]

Celestine Mendler-Dünner

Proceedings of the 37th International Conference on Machine Learning, 2020

An Accelerated DFO Algorithm for Finite-sum Convex Functions.

[BibT_eX]

[DOI]

Yuwen Chen

Proceedings of the 37th International Conference on Machine Learning, 2020

Controlling Style and Semantics in Weakly-Supervised Image Generation.

[BibT_eX]

[DOI]

Dario Pavllo

Proceedings of the Computer Vision - ECCV 2020, 2020

A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

A Stochastic Tensor Method for Non-convex Optimization.

[BibT_eX]

[DOI]

Jonas Kohler

CoRR, 2019

Cosmological N-body simulations: a challenge for scalable generative models.

[BibT_eX]

[DOI]

CoRR, 2019

Ellipsoidal Trust Region Methods and the Marginal Value of Hessian Information for Neural Network Training.

[BibT_eX]

[DOI]

Leonard Adolphs

Jonas Kohler

CoRR, 2019

The Role of Memory in Stochastic Optimization.

[BibT_eX]

[DOI]

Jonas Kohler

Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, 2019

Shadowing Properties of Optimization Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Continuous-time Models for Stochastic Optimization Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Domain Agnostic Measure for Monitoring and Evaluating GANs.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Topological Map Extraction From Overhead Images.

[BibT_eX]

[DOI]

Zuoyue Li

Jan Dirk Wegner

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

Local Saddle Point Optimization: A Curvature Exploitation Approach.

[BibT_eX]

[DOI]

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

PolyMapper: Extracting City Maps using Polygons.

[BibT_eX]

[DOI]

Zuoyue Li

Jan Dirk Wegner

CoRR, 2018

Evaluating GANs via Duality.

[BibT_eX]

[DOI]

CoRR, 2018

Towards a Theoretical Understanding of Batch Normalization.

[BibT_eX]

[DOI]

CoRR, 2018

Adversarially Robust Training through Structured Gradient Regularization.

[BibT_eX]

[DOI]

CoRR, 2018

A Distributed Second-Order Algorithm You Can Trust.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Escaping Saddles with Stochastic Gradients.

[BibT_eX]

[DOI]

Proceedings of the 35th International Conference on Machine Learning, 2018

Semantic Interpolation in Implicit Models.

[BibT_eX]

[DOI]

Yannic Kilcher

Proceedings of the 6th International Conference on Learning Representations, 2018

An Online Learning Approach to Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Learning Aerial Image Segmentation From Online Maps.

[BibT_eX]

[DOI]

IEEE Trans. Geosci. Remote. Sens., 2017

Flexible Prior Distributions for Deep Generative Models.

[BibT_eX]

[DOI]

Yannic Kilcher

CoRR, 2017

Generator Reversal.

[BibT_eX]

[DOI]

Yannic Kilcher

CoRR, 2017

Radio frequency interference mitigation using deep convolutional neural networks.

[BibT_eX]

[DOI]

Astron. Comput., 2017

Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification.

[BibT_eX]

[DOI]

Proceedings of the 26th International Conference on World Wide Web, 2017

Stabilizing Training of Generative Adversarial Networks through Regularization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Sub-sampled Cubic Regularization for Non-convex Optimization.

[BibT_eX]

[DOI]

Jonas Moritz Kohler

Proceedings of the 34th International Conference on Machine Learning, 2017

2016

DynaNewton - Accelerating Newton's Method for Machine Learning.

[BibT_eX]

[DOI]

Hadi Daneshmand

CoRR, 2016

Bootstrap, Review, Decode: Using Out-of-Domain Textual Data to Improve Image Captioning.

[BibT_eX]

[DOI]

Wenhu Chen

CoRR, 2016

Probabilistic Bag-Of-Hyperlinks Model for Entity Linking.

[BibT_eX]

[DOI]

Proceedings of the 25th International Conference on World Wide Web, 2016

SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision.

[BibT_eX]

[DOI]

Proceedings of the 10th International Workshop on Semantic Evaluation, 2016

Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016

Starting Small - Learning with Adaptive Sample Sizes.

[BibT_eX]

[DOI]

Hadi Daneshmand

Proceedings of the 33nd International Conference on Machine Learning, 2016

2015

Learning Structured Models for Segmentation of 2-D and 3-D Imagery.

[BibT_eX]

[DOI]

IEEE Trans. Medical Imaging, 2015

A Variance Reduced Stochastic Newton Method.

[BibT_eX]

[DOI]

Brian McWilliams

CoRR, 2015

Neighborhood Watch: Stochastic Gradient Descent with Neighbors.

[BibT_eX]

[DOI]

Brian McWilliams

CoRR, 2015

Variance Reduced Stochastic Gradient Descent with Neighbors.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

2014

Exploiting Enclosing Membranes and Contextual Cues for Mitochondria Segmentation.

[BibT_eX]

[DOI]

Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2014, 2014

2013

Learning Discriminative Features and Structured Models for Segmentation in Microscopy and Natural Images.

[BibT_eX]

[DOI]

PhD thesis, 2013

Flash Scanning Electron Microscopy.

[BibT_eX]

[DOI]

Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2013, 2013

An Optimal Policy for Target Localization with Application to Electron Microscopy.

[BibT_eX]

[DOI]

Proceedings of the 30th International Conference on Machine Learning, 2013

Learning for Structured Prediction Using Approximate Subgradient Descent with Working Sets.

[BibT_eX]

[DOI]

Yunpeng Li

Pascal Fua

Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

2012

Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features.

[BibT_eX]

[DOI]

IEEE Trans. Medical Imaging, 2012

SLIC Superpixels Compared to State-of-the-Art Superpixel Methods.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2012

Efficient Scanning for EM Based Target Localization.

[BibT_eX]

[DOI]

Raphael Sznitman

Natasa Pjescic-Emedji

Graham Knott

Pascal Fua

Proceedings of the Medical Image Computing and Computer-Assisted Intervention - MICCAI 2012, 2012

Joint Image and Word Sense Discrimination for Image Retrieval.

[BibT_eX]

[DOI]