← Authors

Martin Jaggi

103 papers · 2012–2025 · 15 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (10) 🐝 Cross-Pollinator (13) πŸƒ Academic Marathon (13) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (11) 🌍 Conference Polyglot (15) 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (4) 🏠 Conference Loyalist (28) πŸ‘₯ Mega-Team (24) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (31) 🀝 Dynamic Duo (12) πŸ† Grand Slam πŸ—ƒοΈ Keyword Collector (60) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (14) ⚑ Prolific Year (13) πŸ“ˆ Trend Setter πŸ’Ž Century Club (103)

Conferences

NIPS (28) ICML (26) ICLR (14) AISTATS (12) ACL (5) NAACL (3) SEMEVAL (3) AAAI (2) EMNLP (2) IJCNLP (2) JMLR (2) COLT (1) CONLL (1) ICCV (1) INTERSPEECH (1)

Top co-authors

Sai Praneeth Karimireddy (12) Sebastian Stich (12) Sebastian U Stich (11) Tao LIN (9) Thijs Vogels (8) Matteo Pagliardini (8) Amirkeivan Mohtashami (7) Anastasia Koloskova (7) Prakhar Gupta (6) Nikita Doikov (6)

Keywords

distributed optimization (12) communication efficiency (10) stochastic gradient descent (10) convex optimization (9) federated learning (8) distributed learning (7) representation learning (6) coordinate descent (6) decentralized learning (6) model compression (6) sentence embedding (5) neural network (5) knowledge distillation (5) gradient compression (5) neural network training (4) unsupervised learning (4) word embedding (4) neural network optimization (4) stochastic optimization (3) decentralized optimization (3)

Papers

Improving Stochastic Cubic Newton with Momentum AISTATS 2025
Attention with Markov: A Curious Case of Single-layer Transformers ICLR 2025
Intrinsic User-Centric Interpretability through Global Mixture of Experts ICLR 2025
CoTFormer: A Chain of Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference ICLR 2025
Effective Interplay between Sparsity and Quantization: From Theory to Practice ICLR 2025
On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists ICML 2025
Layer-wise linear mode connectivity ICLR 2024
The Privacy Power of Correlated Noise in Decentralized Learning ICML 2024
Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions ICML 2024
Ghost Noise for Regularizing Deep Neural Networks AAAI 2024
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging NIPS 2024
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs NIPS 2024
LASER: Linear Compression in Wireless Distributed Optimization ICML 2024
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks ICML 2024
DOGE: Domain Reweighting with Generalization Estimation ICML 2024
On Convergence of Incremental Gradient for Non-convex Smooth Functions ICML 2024
Analyzing & Reducing the Need for Learning Rate Warmup in GPT Training NIPS 2024
CoBo: Collaborative Learning via Bilevel Optimization NIPS 2024
Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations NIPS 2024
Random-Access Infinite Context Length for Transformers NIPS 2023
Beyond Spectral Gap: The Role of the Topology in Decentralized Learning JMLR 2023
Agree to Disagree: Diversity through Disagreement for Better Transferability ICLR 2023
Collaborative Learning via Prediction Consensus NIPS 2023
Multiplication-Free Transformer Training via Piecewise Affine Operations NIPS 2023
MultiMoDNβ€”Multimodal, Multi-Task, Interpretable Modular Networks NIPS 2023
Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention NIPS 2023
SIMSUM: Document-level Text Simplification via Simultaneous Summarization ACL 2023
Special Properties of Gradient Descent with Large Learning Rates ICML 2023
Second-Order Optimization with Lazy Hessians ICML 2023
Linearization Algorithms for Fully Composite Optimization COLT 2023
SKILL: Structured Knowledge Infusion for Large Language Models NAACL 2022
Masked Training of Neural Networks with Partial Gradients AISTATS 2022
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing ICLR 2022
Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning NIPS 2022
Beyond spectral gap: the role of the topology in decentralized learning NIPS 2022
Implicit Gradient Alignment in Distributed and Federated Learning AAAI 2022
FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings NIPS 2022
Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data ICML 2021
Consensus Control for Decentralized Deep Learning ICML 2021
Learning from History for Byzantine Robust Optimization ICML 2021
Lightweight Cross-Lingual Sentence Representation Learning IJCNLP 2021
Obtaining Better Static Word Embeddings Using Contextual Embedding Models IJCNLP 2021
Breaking the centralized barrier for cross-device federated learning NIPS 2021
Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates AISTATS 2021
A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! AISTATS 2021
Exact Optimization of Conformal Predictors via Incremental and Decremental Learning ICML 2021
Understanding the effects of data parallelism and sparsity on neural network training ICLR 2021
LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads AISTATS 2021
RelaySum for Decentralized Deep Learning on Heterogeneous Data NIPS 2021
Lightweight Cross-Lingual Sentence Representation Learning ACL 2021
Obtaining Better Static Word Embeddings Using Contextual Embedding Models ACL 2021
Self-Supervised Neural Topic Modeling EMNLP 2021
Semantic Perturbations With Normalizing Flows for Improved Generalization ICCV 2021
Taming GANs with Lookahead-Minmax ICLR 2021
Optimizer Benchmarking Needs to Account for Hyperparameter Tuning ICML 2020
Ensemble Distillation for Robust Model Fusion in Federated Learning NIPS 2020
Practical Low-Rank Communication Compression in Decentralized Deep Learning NIPS 2020
Model Fusion via Optimal Transport NIPS 2020
Linearly Convergent Frank-Wolfe with Backtracking Line-Search AISTATS 2020
Context Mover’s Distance & Barycenters: Optimal Transport of Contexts for Building Representations AISTATS 2020
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models EMNLP 2020
Dynamic Model Pruning with Feedback ICLR 2020
On the Relationship between Self-Attention and Convolutional Layers ICLR 2020
Decentralized Deep Learning with Arbitrary Communication Compression ICLR 2020
Don't Use Large Mini-batches, Use Local SGD ICLR 2020
Evaluating The Search Phase of Neural Architecture Search ICLR 2020
A Unified Theory of Decentralized SGD with Changing Topology and Local Updates ICML 2020
Extrapolation for Large-batch Training in Deep Learning ICML 2020
Correlating Twitter Language with Community-Level Health Outcomes ACL 2019
Better Word Embeddings by Disentangling Contextual n-Gram Information NAACL 2019
Open-Vocabulary Keyword Spotting with Audio and Text Embeddings INTERSPEECH 2019
Efficient Greedy Coordinate Descent for Composite Problems AISTATS 2019
Unsupervised Scalable Representation Learning for Multivariate Time Series NIPS 2019
Overcoming Multi-model Forgetting ICML 2019
Error Feedback Fixes SignSGD and other Gradient Compression Schemes ICML 2019
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication ICML 2019
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization NIPS 2019
Adaptive balancing of gradient and update computation times using global geometry and approximate subproblems AISTATS 2018
A Distributed Second-Order Algorithm You Can Trust ICML 2018
On Matching Pursuit and Coordinate Descent ICML 2018
Simple Unsupervised Keyphrase Extraction using Sentence Embeddings CONLL 2018
CoCoA: A General Framework for Communication-Efficient Distributed Optimization JMLR 2018
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features NAACL 2018
Sparsified SGD with Memory NIPS 2018
Training DNNs with Hybrid Block Floating Point NIPS 2018
COLA: Decentralized Linear Learning NIPS 2018
Generating Steganographic Text with LSTMs ACL 2017
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe AISTATS 2017
Safe Adaptive Importance Sampling NIPS 2017
Approximate Steepest Coordinate Descent ICML 2017
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems NIPS 2017
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees NIPS 2017
Faster Coordinate Descent via Adaptive Importance Sampling AISTATS 2017
Primal-Dual Rates and Certificates ICML 2016
SwissCheese at SemEval-2016 Task 4: Sentiment Classification Using an Ensemble of Convolutional Neural Networks with Distant Supervision SEMEVAL 2016
Adding vs. Averaging in Distributed Primal-Dual Optimization ICML 2015
Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment SEMEVAL 2015
On the Global Linear Convergence of Frank-Wolfe Optimization Variants NIPS 2015
Communication-Efficient Distributed Dual Coordinate Ascent NIPS 2014
Swiss-Chocolate: Sentiment Detection using Sparse SVMs and Part-Of-Speech n-Grams SEMEVAL 2014
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization ICML 2013
Block-Coordinate Frank-Wolfe Optimization for Structural SVMs ICML 2013
Regularization Paths with Guarantees for Convex Semidefinite Optimization AISTATS 2012