Martin Jaggi

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

2020

Sparse Communication for Training Deep Networks.

[BibT_eX]

[DOI]

Negar Foroutan Eghlidi

CoRR, 2020

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning.

[BibT_eX]

[DOI]

Ananda Theertha Suresh

CoRR, 2020

PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning.

[BibT_eX]

[DOI]

Thijs Vogels

CoRR, 2020

Multi-Head Attention: Collaborate Instead of Concatenate.

[BibT_eX]

[DOI]

Andreas Loukas

CoRR, 2020

Taming GANs with Lookahead.

[BibT_eX]

[DOI]

CoRR, 2020

Byzantine-Robust Learning on Heterogeneous Datasets via Resampling.

[BibT_eX]

[DOI]

CoRR, 2020

Secure Byzantine-Robust Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2020

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models.

[BibT_eX]

[DOI]

CoRR, 2020

Data Parallelism in Training Sparse Neural Networks.

[BibT_eX]

[DOI]

Namhoon Lee

Philip H. S. Torr

CoRR, 2020

Practical Low-Rank Communication Compression in Decentralized Deep Learning.

[BibT_eX]

[DOI]

Thijs Vogels

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

Model Fusion via Optimal Transport.

[BibT_eX]

[DOI]

Sidak Pal Singh

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

Ensemble Distillation for Robust Model Fusion in Federated Learning.

[BibT_eX]

[DOI]

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

Weight Erosion: An Update Aggregation Scheme for Personalized Collaborative Machine Learning.

[BibT_eX]

[DOI]

Felix Grimberg

Mary-Anne Hartley

Proceedings of the Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning, 2020

Optimizer Benchmarking Needs to Account for Hyperparameter Tuning.

[BibT_eX]

[DOI]

Prabhu Teja Sivaprasad

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

Extrapolation for Large-batch Training in Deep Learning.

[BibT_eX]

[DOI]

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

A Unified Theory of Decentralized SGD with Changing Topology and Local Updates.

[BibT_eX]

[DOI]

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

Evaluating The Search Phase of Neural Architecture Search.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Don't Use Large Mini-batches, Use Local SGD.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Dynamic Model Pruning with Feedback.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Decentralized Deep Learning with Arbitrary Communication Compression.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

On the Relationship between Self-Attention and Convolutional Layers.

[BibT_eX]

[DOI]

Andreas Loukas

Proceedings of the 8th International Conference on Learning Representations, 2020

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020

Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations.

[BibT_eX]

[DOI]

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

Linearly Convergent Frank-Wolfe without Line-Search.

[BibT_eX]

[DOI]

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

2019

Unsupervised robust nonparametric learning of hidden community properties.

[BibT_eX]

[DOI]

Mikhail A. Langovoy

Akhilesh Gotmare

Math. Found. Comput., 2019

Robust Cross-lingual Embeddings from Parallel Sentences.

[BibT_eX]

[DOI]

Ali Sabet

Robert West

Dimitris S. Papailiopoulos

CoRR, 2019

Advances and Open Problems in Federated Learning.

[BibT_eX]

[DOI]

Rafael G. L. D'Oliveira

Ananda Theertha Suresh

CoRR, 2019

On the Tunability of Optimizers in Deep Learning.

[BibT_eX]

[DOI]

Prabhu Teja Sivaprasad

CoRR, 2019

SysML: The New Frontier of Machine Learning Systems.

[BibT_eX]

[DOI]

Alexandros G. Dimakis

Anastasios Kyrillidis

Shivaram Venkataraman

CoRR, 2019

Structure Tree-LSTM: Structure-aware Attentional Document Encoders.

[BibT_eX]

[DOI]

CoRR, 2019

Forecasting intracranial hypertension using multi-scale waveform metrics.

[BibT_eX]

[DOI]

CoRR, 2019

Crosslingual Document Embedding as Reduced-Rank Ridge Regression.

[BibT_eX]

[DOI]

Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, 2019

Correlating Twitter Language with Community-Level Health Outcomes.

[BibT_eX]

[DOI]

Proceedings of the Fourth Social Media Mining for Health Application Workshop & Shared Task, 2019

PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization.

[BibT_eX]

[DOI]

Thijs Vogels

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

Unsupervised Scalable Representation Learning for Multivariate Time Series.

[BibT_eX]

[DOI]

Jean-Yves Franceschi

Aymeric Dieuleveut

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

Better Word Embeddings by Disentangling Contextual n-Gram Information.

[BibT_eX]

[DOI]

Matteo Pagliardini

Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019

Open-Vocabulary Keyword Spotting with Audio and Text Embeddings.

[BibT_eX]

[DOI]

Proceedings of the 20th Annual Conference of the International Speech Communication Association, 2019

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication.

[BibT_eX]

[DOI]

Anastasia Koloskova

Proceedings of the 36th International Conference on Machine Learning, 2019

Error Feedback Fixes SignSGD and other Gradient Compression Schemes.

[BibT_eX]

[DOI]

Quentin Rebjock

Proceedings of the 36th International Conference on Machine Learning, 2019

Overcoming Multi-model Forgetting.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

On Linear Learning with Manycore Processors.

[BibT_eX]

[DOI]

Eliza Wszola

Celestine Mendler-Dünner

Markus Püschel

Proceedings of the 26th IEEE International Conference on High Performance Computing, 2019

Efficient Greedy Coordinate Descent for Composite Problems.

[BibT_eX]

[DOI]

Anastasia Koloskova

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

2018

Optimal Affine-Invariant Smooth Minimization Algorithms.

[BibT_eX]

[DOI]

Alexandre d'Aspremont

Cristóbal Guzmán

SIAM J. Optim., 2018

Wasserstein is all you need.

[BibT_eX]

[DOI]

CoRR, 2018

Don't Use Large Mini-Batches, Use Local SGD.

[BibT_eX]

[DOI]

Tao Lin

CoRR, 2018

COLA: Communication-Efficient Decentralized Linear Learning.

[BibT_eX]

[DOI]

An Bian

CoRR, 2018

Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients.

[BibT_eX]

[DOI]

CoRR, 2018

End-to-End DNN Training with Block Floating Point Arithmetic.

[BibT_eX]

[DOI]

CoRR, 2018

Revisiting First-Order Convex Optimization Over Linear Spaces.

[BibT_eX]

[DOI]

Francesco Locatello

CoRR, 2018

EmbedRank: Unsupervised Keyphrase Extraction using Sentence Embeddings.

[BibT_eX]

[DOI]

CoRR, 2018

Sparsified SGD with Memory.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

COLA: Decentralized Linear Learning.

[BibT_eX]

[DOI]

An Bian

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Training DNNs with Hybrid Block Floating Point.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features.

[BibT_eX]

[DOI]

Matteo Pagliardini

Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018

On Matching Pursuit and Coordinate Descent.

[BibT_eX]

[DOI]

Francesco Locatello

Sai Praneeth Reddy Karimireddy

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

A Distributed Second-Order Algorithm You Can Trust.

[BibT_eX]

[DOI]

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

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings.

[BibT_eX]

[DOI]

Proceedings of the 22nd Conference on Computational Natural Language Learning, 2018

Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2018

2017

Learning Aerial Image Segmentation From Online Maps.

[BibT_eX]

[DOI]

IEEE Trans. Geosci. Remote. Sens., 2017

Distributed optimization with arbitrary local solvers.

[BibT_eX]

[DOI]

Optim. Methods Softw., 2017

CoCoA: A General Framework for Communication-Efficient Distributed Optimization.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2017

Efficient Use of Limited-Memory Resources to Accelerate Linear Learning.

[BibT_eX]

[DOI]

Celestine Dünner

Thomas P. Parnell

CoRR, 2017

Unsupervised robust nonparametric learning of hidden community properties.

[BibT_eX]

[DOI]

CoRR, 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

Safe Adaptive Importance Sampling.

[BibT_eX]

[DOI]

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

Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees.

[BibT_eX]

[DOI]

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

Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems.

[BibT_eX]

[DOI]

Celestine Dünner

Thomas P. Parnell

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

Approximate Steepest Coordinate Descent.

[BibT_eX]

[DOI]

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

Faster Coordinate Descent via Adaptive Importance Sampling.

[BibT_eX]

[DOI]

Dmytro Perekrestenko

Volkan Cevher

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe.

[BibT_eX]

[DOI]

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 2017

Generating Steganographic Text with LSTMs.

[BibT_eX]

[DOI]

Tina Fang

Katerina J. Argyraki

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017

2016

Screening Rules for Convex Problems.

[BibT_eX]

[DOI]

CoRR, 2016

Pursuits in Structured Non-Convex Matrix Factorizations.

[BibT_eX]

[DOI]

Rajiv Khanna

Michael Tschannen

CoRR, 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

Primal-Dual Rates and Certificates.

[BibT_eX]

[DOI]

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

Audio Based Bird Species Identification using Deep Learning Techniques.

[BibT_eX]

[DOI]

Proceedings of the Working Notes of CLEF 2016, 2016

2015

L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework.

[BibT_eX]

[DOI]

CoRR, 2015

Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment.

[BibT_eX]

[DOI]

Proceedings of the 9th International Workshop on Semantic Evaluation, 2015

On the Global Linear Convergence of Frank-Wolfe Optimization Variants.

[BibT_eX]

[DOI]

Simon Lacoste-Julien

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

Adding vs. Averaging in Distributed Primal-Dual Optimization.

[BibT_eX]

[DOI]

Proceedings of the 32nd International Conference on Machine Learning, 2015

2014

Swiss-Chocolate: Sentiment Detection using Sparse SVMs and Part-Of-Speech n-Grams.

[BibT_eX]

[DOI]

Fatih Uzdilli

Mark Cieliebak

Proceedings of the 8th International Workshop on Semantic Evaluation, 2014

Communication-Efficient Distributed Dual Coordinate Ascent.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

2013

An Equivalence between the Lasso and Support Vector Machines

[BibT_eX]

[DOI]

CoRR, 2013

Block-Coordinate Frank-Wolfe Optimization for Structural SVMs.

[BibT_eX]

[DOI]

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

Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization.

[BibT_eX]

[DOI]

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

2012

Approximating parameterized convex optimization problems.

[BibT_eX]

[DOI]

Sören Laue

ACM Trans. Algorithms, 2012

An Exponential Lower Bound on the Complexity of Regularization Paths.

[BibT_eX]

[DOI]

Bernd Gärtner

Clément Maria

J. Comput. Geom., 2012

Regularization Paths with Guarantees for Convex Semidefinite Optimization.

[BibT_eX]

[DOI]

Sören Laue

Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, 2012

Stochastic Block-Coordinate Frank-Wolfe Optimization for Structural SVMs

[BibT_eX]

[DOI]

CoRR, 2012

Optimizing over the Growing Spectrahedron.

[BibT_eX]

[DOI]

Sören Laue

Proceedings of the Algorithms - ESA 2012, 2012

2011

Sparse Convex Optimization Methods for Machine Learning.

[BibT_eX]

[DOI]

PhD thesis, 2011

Convex Optimization without Projection Steps

[BibT_eX]

[DOI]

CoRR, 2011

2010

A Simple Algorithm for Nuclear Norm Regularized Problems.

[BibT_eX]

[DOI]

Marek Sulovský

Proceedings of the 27th International Conference on Machine Learning (ICML-10), 2010

2009

A Combinatorial Algorithm to Compute Regularization Paths

[BibT_eX]

[DOI]

CoRR, 2009

An Exponential Lower Bound on the Complexity of Regularization Paths

[BibT_eX]

[DOI]

Bernd Gärtner

CoRR, 2009

Coresets for polytope distance.

[BibT_eX]

[DOI]

Bernd Gärtner