Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMartin Jaggi
Person information
- affiliation: EPFL, School of Computer and Communication Sciences, Lausanne, Switzerland
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2023
[c87]Sofia Blinova, Xinyu Zhou, Martin Jaggi, Carsten Eickhoff, Seyed Ali Bahrainian:
SIMSUM: Document-level Text Simplification via Simultaneous Summarization. ACL (1) 2023: 9927-9944- [c86]Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion:
Linearization Algorithms for Fully Composite Optimization. COLT 2023: 3669-3695 - [c85]Matteo Pagliardini, Martin Jaggi, François Fleuret, Sai Praneeth Karimireddy:
Agree to Disagree: Diversity through Disagreement for Better Transferability. ICLR 2023 - [c84]Nikita Doikov, El Mahdi Chayti, Martin Jaggi:
Second-Order Optimization with Lazy Hessians. ICML 2023: 8138-8161 - [c83]Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich:
Special Properties of Gradient Descent with Large Learning Rates. ICML 2023: 25082-25104 - [i121]Thijs Vogels, Hadrien Hendrikx, Martin Jaggi:
Beyond spectral gap (extended): The role of the topology in decentralized learning. CoRR abs/2301.02151 (2023) - [i120]El Mahdi Chayti, Nikita Doikov, Martin Jaggi:
Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods. CoRR abs/2302.11962 (2023) - [i119]Maria-Luiza Vladarean, Nikita Doikov, Martin Jaggi, Nicolas Flammarion:
Linearization Algorithms for Fully Composite Optimization. CoRR abs/2302.12808 (2023) - [i118]Amirkeivan Mohtashami, Martin Jaggi:
Landmark Attention: Random-Access Infinite Context Length for Transformers. CoRR abs/2305.16300 (2023) - [i117]Atli Kosson, Martin Jaggi:
Hardware-Efficient Transformer Training via Piecewise Affine Operations. CoRR abs/2305.17190 (2023) - [i116]Atli Kosson, Dongyang Fan, Martin Jaggi:
Ghost Noise for Regularizing Deep Neural Networks. CoRR abs/2305.17205 (2023) - [i115]Atli Kosson, Bettina Messmer, Martin Jaggi:
Rotational Optimizers: Simple & Robust DNN Training. CoRR abs/2305.17212 (2023) - [i114]Dongyang Fan, Celestine Mendler-Dünner, Martin Jaggi:
Collaborative Learning via Prediction Consensus. CoRR abs/2305.18497 (2023) - [i113]Anastasia Koloskova, Nikita Doikov, Sebastian U. Stich, Martin Jaggi:
Shuffle SGD is Always Better than SGD: Improved Analysis of SGD with Arbitrary Data Orders. CoRR abs/2305.19259 (2023) - [i112]Matteo Pagliardini, Daniele Paliotta, Martin Jaggi, François Fleuret:
Faster Causal Attention Over Large Sequences Through Sparse Flash Attention. CoRR abs/2306.01160 (2023) - [i111]Mariel A. Werner, Lie He, Sai Praneeth Karimireddy, Michael I. Jordan, Martin Jaggi:
Provably Personalized and Robust Federated Learning. CoRR abs/2306.08393 (2023) - [i110]Linara Adilova, Asja Fischer, Martin Jaggi:
Layerwise Linear Mode Connectivity. CoRR abs/2307.06966 (2023) - [i109]Vinitra Swamy, Malika Satayeva, Jibril Frej, Thierry Bossy, Thijs Vogels, Martin Jaggi, Tanja Käser, Mary-Anne Hartley:
MultiModN- Multimodal, Multi-Task, Interpretable Modular Networks. CoRR abs/2309.14118 (2023) - [i108]Amirkeivan Mohtashami, Matteo Pagliardini, Martin Jaggi:
CoTFormer: More Tokens With Attention Make Up For Less Depth. CoRR abs/2310.10845 (2023) - [i107]Ashok Vardhan Makkuva, Marco Bondaschi, Thijs Vogels, Martin Jaggi, Hyeji Kim, Michael C. Gastpar:
LASER: Linear Compression in Wireless Distributed Optimization. CoRR abs/2310.13033 (2023) - [i106]Simin Fan, Martin Jaggi:
Irreducible Curriculum for Language Model Pretraining. CoRR abs/2310.15389 (2023) - [i105]Simin Fan, Matteo Pagliardini, Martin Jaggi:
DoGE: Domain Reweighting with Generalization Estimation. CoRR abs/2310.15393 (2023) - [i104]Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff:
Controllable Topic-Focused Abstractive Summarization. CoRR abs/2311.06724 (2023) - 2022
- [c82]Yatin Dandi, Luis Barba, Martin Jaggi:
Implicit Gradient Alignment in Distributed and Federated Learning. AAAI 2022: 6454-6462 - [c81]Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich:
Masked Training of Neural Networks with Partial Gradients. AISTATS 2022: 5876-5890 - [c80]Sai Praneeth Karimireddy, Lie He, Martin Jaggi:
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing. ICLR 2022 - [c79]Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi:
SKILL: Structured Knowledge Infusion for Large Language Models. NAACL-HLT 2022: 1581-1588 - [c78]Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi:
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning. NeurIPS 2022 - [c77]Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Telenczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux:
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings. NeurIPS 2022 - [c76]Thijs Vogels, Hadrien Hendrikx, Martin Jaggi:
Beyond spectral gap: the role of the topology in decentralized learning. NeurIPS 2022 - [i103]Lie He, Sai Praneeth Karimireddy, Martin Jaggi:
Byzantine-Robust Decentralized Learning via Self-Centered Clipping. CoRR abs/2202.01545 (2022) - [i102]Amirkeivan Mohtashami, Sebastian U. Stich, Martin Jaggi:
Characterizing & Finding Good Data Orderings for Fast Convergence of Sequential Gradient Methods. CoRR abs/2202.01838 (2022) - [i101]Matteo Pagliardini, Martin Jaggi, François Fleuret, Sai Praneeth Karimireddy:
Agree to Disagree: Diversity through Disagreement for Better Transferability. CoRR abs/2202.04414 (2022) - [i100]Matteo Pagliardini, Gilberto Manunza, Martin Jaggi, Michael I. Jordan, Tatjana Chavdarova:
Improving Generalization via Uncertainty Driven Perturbations. CoRR abs/2202.05737 (2022) - [i99]Yatin Dandi, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich:
Data-heterogeneity-aware Mixing for Decentralized Learning. CoRR abs/2204.06477 (2022) - [i98]Fedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi:
SKILL: Structured Knowledge Infusion for Large Language Models. CoRR abs/2205.08184 (2022) - [i97]Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich:
On Avoiding Local Minima Using Gradient Descent With Large Learning Rates. CoRR abs/2205.15142 (2022) - [i96]Thijs Vogels, Hadrien Hendrikx, Martin Jaggi:
Beyond spectral gap: The role of the topology in decentralized learning. CoRR abs/2206.03093 (2022) - [i95]Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi:
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning. CoRR abs/2206.08307 (2022) - [i94]Jean Ogier du Terrail, Samy-Safwan Ayed, Edwige Cyffers, Felix Grimberg, Chaoyang He, Regis Loeb, Paul Mangold, Tanguy Marchand, Othmane Marfoq, Erum Mushtaq, Boris Muzellec, Constantin Philippenko, Santiago Silva, Maria Telenczuk, Shadi Albarqouni, Salman Avestimehr, Aurélien Bellet, Aymeric Dieuleveut, Martin Jaggi, Sai Praneeth Karimireddy, Marco Lorenzi, Giovanni Neglia, Marc Tommasi, Mathieu Andreux:
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings. CoRR abs/2210.04620 (2022) - [i93]Cécile Trottet
, Thijs Vogels, Martin Jaggi, Mary-Anne Hartley:
Modular Clinical Decision Support Networks (MoDN) - Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments. CoRR abs/2211.06637 (2022) - [i92]Simla Burcu Harma, Canberk Sönmez, Babak Falsafi, Martin Jaggi, Yunho Oh:
Accuracy Boosters: Epoch-Driven Mixed-Mantissa Block Floating-Point for DNN Training. CoRR abs/2211.10737 (2022) - [i91]Frédéric Berdoz, Abhishek Singh, Martin Jaggi, Ramesh Raskar:
Scalable Collaborative Learning via Representation Sharing. CoRR abs/2211.10943 (2022) - [i90]Nikita Doikov, El Mahdi Chayti, Martin Jaggi:
Second-order optimization with lazy Hessians. CoRR abs/2212.00781 (2022) - 2021
- [j9]Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aurélien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista A. Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D'Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adrià Gascón, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaïd Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecný, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrède Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Özgür, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramèr, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, Sen Zhao:
Advances and Open Problems in Federated Learning. Found. Trends Mach. Learn. 14(1-2): 1-210 (2021) - [j8]Chenxin Ma, Martin Jaggi, Frank E. Curtis, Nathan Srebro, Martin Takác:
An accelerated communication-efficient primal-dual optimization framework for structured machine learning. Optim. Methods Softw. 36(1): 20-44 (2021) - [c75]Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, Sadao Kurohashi:
Lightweight Cross-Lingual Sentence Representation Learning. ACL/IJCNLP (1) 2021: 2902-2913 - [c74]Prakhar Gupta, Martin Jaggi:
Obtaining Better Static Word Embeddings Using Contextual Embedding Models. ACL/IJCNLP (1) 2021: 5241-5253 - [c73]Hossein Shokri Ghadikolaei, Sebastian U. Stich, Martin Jaggi:
LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads. AISTATS 2021: 3943-3951 - [c72]Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi:
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates. AISTATS 2021: 4042-4050 - [c71]Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich:
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! AISTATS 2021: 4087-4095 - [c70]Seyed Ali Bahrainian, Martin Jaggi, Carsten Eickhoff:
Self-Supervised Neural Topic Modeling. EMNLP (Findings) 2021: 3341-3350 - [c69]Eliza Wszola, Martin Jaggi, Markus Püschel:
Faster Parallel Training of Word Embeddings. HiPC 2021: 31-41 - [c68]Oguz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova:
Semantic Perturbations with Normalizing Flows for Improved Generalization. ICCV 2021: 6599-6609 - [c67]Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich, François Fleuret, Martin Jaggi:
Taming GANs with Lookahead-Minmax. ICLR 2021 - [c66]Namhoon Lee, Thalaiyasingam Ajanthan, Philip H. S. Torr, Martin Jaggi:
Understanding the effects of data parallelism and sparsity on neural network training. ICLR 2021 - [c65]Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi:
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning. ICML 2021: 1836-1845 - [c64]Sai Praneeth Karimireddy, Lie He, Martin Jaggi:
Learning from History for Byzantine Robust Optimization. ICML 2021: 5311-5319 - [c63]Lingjing Kong, Tao Lin, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich:
Consensus Control for Decentralized Deep Learning. ICML 2021: 5686-5696 - [c62]Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi:
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data. ICML 2021: 6654-6665 - [c61]Mario Drumond, Louis Coulon, Arash Pourhabibi Zarandi, Ahmet Caner Yüzügüler, Babak Falsafi, Martin Jaggi:
Equinox: Training (for Free) on a Custom Inference Accelerator. MICRO 2021: 421-433 - [c60]Mariko Makhmutova, Raghu Kainkaryam, Marta Ferreira, Jae Min, Martin Jaggi, Ieuan Clay:
Prediction of self-reported depression scores using person-generated health data from a virtual 1-year mental health observational study. DigiBiom@MobiSys 2021: 4-11 - [c59]Thijs Vogels, Lie He, Anastasia Koloskova, Sai Praneeth Karimireddy, Tao Lin, Sebastian U. Stich, Martin Jaggi:
RelaySum for Decentralized Deep Learning on Heterogeneous Data. NeurIPS 2021: 28004-28015 - [c58]Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh:
Breaking the centralized barrier for cross-device federated learning. NeurIPS 2021: 28663-28676 - [i89]Giovanni Cherubin, Konstantinos Chatzikokolakis, Martin Jaggi:
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning. CoRR abs/2102.03236 (2021) - [i88]Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi:
Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data. CoRR abs/2102.04761 (2021) - [i87]Lingjing Kong, Tao Lin, Anastasia Koloskova, Martin Jaggi, Sebastian U. Stich:
Consensus Control for Decentralized Deep Learning. CoRR abs/2102.04828 (2021) - [i86]Sebastian U. Stich, Amirkeivan Mohtashami, Martin Jaggi:
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates. CoRR abs/2103.02351 (2021) - [i85]Valerian Rey, Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán, Gérôme Bovet, Martin Jaggi:
Federated Learning for Malware Detection in IoT Devices. CoRR abs/2104.09994 (2021) - [i84]Zhuoyuan Mao, Prakhar Gupta, Chenhui Chu, Martin Jaggi, Sadao Kurohashi:
Lightweight Cross-Lingual Sentence Representation Learning. CoRR abs/2105.13856 (2021) - [i83]Prakhar Gupta, Martin Jaggi:
Obtaining Better Static Word Embeddings Using Contextual Embedding Models. CoRR abs/2106.04302 (2021) - [i82]Amirkeivan Mohtashami, Martin Jaggi, Sebastian U. Stich:
Simultaneous Training of Partially Masked Neural Networks. CoRR abs/2106.08895 (2021) - [i81]Yatin Dandi, Luis Barba, Martin Jaggi:
Implicit Gradient Alignment in Distributed and Federated Learning. CoRR abs/2106.13897 (2021) - [i80]David Roschewitz, Mary-Anne Hartley, Luca Corinzia, Martin Jaggi:
IFedAvg: Interpretable Data-Interoperability for Federated Learning. CoRR abs/2107.06580 (2021) - [i79]Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H. Brendan McMahan, Blaise Agüera y Arcas, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, Suhas N. Diggavi, Hubert Eichner, Advait Gadhikar, Zachary Garrett, Antonious M. Girgis, Filip Hanzely, Andrew Hard, Chaoyang He, Samuel Horváth, Zhouyuan Huo, Alex Ingerman, Martin Jaggi, Tara Javidi, Peter Kairouz, Satyen Kale, Sai Praneeth Karimireddy, Jakub Konecný, Sanmi Koyejo, Tian Li, Luyang Liu, Mehryar Mohri, Hang Qi, Sashank J. Reddi, Peter Richtárik, Karan Singhal, Virginia Smith, Mahdi Soltanolkotabi, Weikang Song, Ananda Theertha Suresh, Sebastian U. Stich, Ameet Talwalkar, Hongyi Wang, Blake E. Woodworth, Shanshan Wu, Felix X. Yu, Honglin Yuan, Manzil Zaheer, Mi Zhang, Tong Zhang, Chunxiang Zheng, Chen Zhu, Wennan Zhu:
A Field Guide to Federated Optimization. CoRR abs/2107.06917 (2021) - [i78]Oguz Kaan Yüksel, Sebastian U. Stich, Martin Jaggi, Tatjana Chavdarova:
Semantic Perturbations with Normalizing Flows for Improved Generalization. CoRR abs/2108.07958 (2021) - [i77]Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian U. Stich:
On Second-order Optimization Methods for Federated Learning. CoRR abs/2109.02388 (2021) - [i76]Thijs Vogels, Lie He, Anastasia Koloskova, Tao Lin, Sai Praneeth Karimireddy, Sebastian U. Stich, Martin Jaggi:
RelaySum for Decentralized Deep Learning on Heterogeneous Data. CoRR abs/2110.04175 (2021) - [i75]Martin Beaussart, Felix Grimberg, Mary-Anne Hartley, Martin Jaggi:
WAFFLE: Weighted Averaging for Personalized Federated Learning. CoRR abs/2110.06978 (2021) - [i74]Felix Grimberg, Mary-Anne Hartley, Sai Praneeth Karimireddy, Martin Jaggi:
Optimal Model Averaging: Towards Personalized Collaborative Learning. CoRR abs/2110.12946 (2021) - [i73]El Mahdi Chayti, Sai Praneeth Karimireddy, Sebastian U. Stich, Nicolas Flammarion, Martin Jaggi:
Linear Speedup in Personalized Collaborative Learning. CoRR abs/2111.05968 (2021) - [i72]Vinitra Swamy, Angelika Romanou, Martin Jaggi:
Interpreting Language Models Through Knowledge Graph Extraction. CoRR abs/2111.08546 (2021) - [i71]Futong Liu, Tao Lin, Martin Jaggi:
Understanding Memorization from the Perspective of Optimization via Efficient Influence Estimation. CoRR abs/2112.08798 (2021) - 2020
- [c57]Fabian Pedregosa, Geoffrey Négiar, Armin Askari, Martin Jaggi:
Linearly Convergent Frank-Wolfe without Line-Search. AISTATS 2020: 1-10 - [c56]Sidak Pal Singh, Andreas Hug, Aymeric Dieuleveut, Martin Jaggi:
Context Mover's Distance & Barycenters: Optimal Transport of Contexts for Building Representations. AISTATS 2020: 3437-3449 - [c55]Mengjie Zhao, Tao Lin, Fei Mi, Martin Jaggi, Hinrich Schütze:
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models. EMNLP (1) 2020: 2226-2241 - [c54]Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi:
On the Relationship between Self-Attention and Convolutional Layers. ICLR 2020 - [c53]Anastasia Koloskova, Tao Lin, Sebastian U. Stich, Martin Jaggi:
Decentralized Deep Learning with Arbitrary Communication Compression. ICLR 2020 - [c52]Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi:
Dynamic Model Pruning with Feedback. ICLR 2020 - [c51]Tao Lin, Sebastian U. Stich, Kumar Kshitij Patel, Martin Jaggi:
Don't Use Large Mini-batches, Use Local SGD. ICLR 2020 - [c50]Kaicheng Yu, Christian Sciuto, Martin Jaggi, Claudiu Musat, Mathieu Salzmann:
Evaluating The Search Phase of Neural Architecture Search. ICLR 2020 - [c49]Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich:
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates. ICML 2020: 5381-5393 - [c48]Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi:
Extrapolation for Large-batch Training in Deep Learning. ICML 2020: 6094-6104 - [c47]Prabhu Teja Sivaprasad, Florian Mai, Thijs Vogels, Martin Jaggi, François Fleuret:
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning. ICML 2020: 9036-9045 - [c46]Felix Grimberg, Mary-Anne Hartley, Martin Jaggi, Sai Praneeth Karimireddy:
Weight Erosion: An Update Aggregation Scheme for Personalized Collaborative Machine Learning. DART/DCL@MICCAI 2020: 160-169 - [c45]Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi:
Ensemble Distillation for Robust Model Fusion in Federated Learning. NeurIPS 2020 - [c44]Sidak Pal Singh, Martin Jaggi:
Model Fusion via Optimal Transport. NeurIPS 2020 - [c43]Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi:
Practical Low-Rank Communication Compression in Decentralized Deep Learning. NeurIPS 2020 - [i70]Anastasia Koloskova, Nicolas Loizou, Sadra Boreiri, Martin Jaggi, Sebastian U. Stich:
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates. CoRR abs/2003.10422 (2020) - [i69]Namhoon Lee, Philip H. S. Torr, Martin Jaggi:
Data Parallelism in Training Sparse Neural Networks. CoRR abs/2003.11316 (2020) - [i68]Mengjie Zhao, Tao Lin, Martin Jaggi, Hinrich Schütze:
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models. CoRR abs/2004.12406 (2020) - [i67]Lie He, Sai Praneeth Karimireddy, Martin Jaggi:
Secure Byzantine-Robust Machine Learning. CoRR abs/2006.04747 (2020) - [i66]Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi:
Extrapolation for Large-batch Training in Deep Learning. CoRR abs/2006.05720 (2020) - [i65]Tao Lin, Lingjing Kong, Sebastian U. Stich, Martin Jaggi:
Ensemble Distillation for Robust Model Fusion in Federated Learning. CoRR abs/2006.07242 (2020) - [i64]Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi:
Dynamic Model Pruning with Feedback. CoRR abs/2006.07253 (2020) - [i63]Lie He, Sai Praneeth Karimireddy, Martin Jaggi:
Byzantine-Robust Learning on Heterogeneous Datasets via Resampling. CoRR abs/2006.09365 (2020) - [i62]Tatjana Chavdarova, Matteo Pagliardini, Martin Jaggi, François Fleuret:
Taming GANs with Lookahead. CoRR abs/2006.14567 (2020) - [i61]Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi:
Multi-Head Attention: Collaborate Instead of Concatenate. CoRR abs/2006.16362 (2020) - [i60]Thijs Vogels, Sai Praneeth Karimireddy, Martin Jaggi:
PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning. CoRR abs/2008.01425 (2020) - [i59]Sai Praneeth Karimireddy, Martin Jaggi, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh:
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning. CoRR abs/2008.03606 (2020) - [i58]Negar Foroutan Eghlidi, Martin Jaggi:
Sparse Communication for Training Deep Networks. CoRR abs/2009.09271 (2020) - [i57]Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtárik, Sebastian U. Stich:
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! CoRR abs/2011.01697 (2020) - [i56]Sai Praneeth Karimireddy, Lie He, Martin Jaggi:
Learning from History for Byzantine Robust Optimization. CoRR abs/2012.10333 (2020)
2010 – 2019
- 2019
- [j7]Mikhail A. Langovoy, Akhilesh Gotmare, Martin Jaggi:
Unsupervised robust nonparametric learning of hidden community properties. Math. Found. Comput. 2(2): 127-147 (2019) - [c42]Sai Praneeth Karimireddy, Anastasia Koloskova, Sebastian U. Stich, Martin Jaggi:
Efficient Greedy Coordinate Descent for Composite Problems. AISTATS 2019: 2887-2896 - [c41]Eliza Wszola, Celestine Mendler-Dünner, Martin Jaggi, Markus Püschel:
On Linear Learning with Manycore Processors. HiPC 2019: 184-194 - [c40]