Martin Jaggi
Identifiers
- name variant Martin Jaggi 0.60 · backfill
Papers (49)
- Local MixVR: Breaking the Communication-Sample Dependence in Distributed Learning cs.LG · 2026 · author #4
- Apertus LLM Family Expansion via Distillation and Quantization cs.LG · 2026 · author #3
- Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection cs.CL · 2026 · author #4
- An Engineering Journey Training Large Language Models at Scale on Alps: The Apertus Experience cs.DC · 2026 · author #17
- Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining cs.CL · 2025 · author #4
- A Split-Client Approach to Second-Order Optimization math.OC · 2025 · author #2
- MEDITRON-70B: Scaling Medical Pretraining for Large Language Models cs.CL · 2023 · author #19
- Correlating Twitter Language with Community-Level Health Outcomes cs.CL · 2019 · author #5
- Better Word Embeddings by Disentangling Contextual n-Gram Information cs.CL · 2019 · author #3
- Crosslingual Document Embedding as Reduced-Rank Ridge Regression cs.CL · 2019 · author #4
- Overcoming Multi-Model Forgetting cs.LG · 2019 · author #4
- Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication cs.LG · 2019 · author #3
- Error Feedback Fixes SignSGD and other Gradient Compression Schemes cs.LG · 2019 · author #4
- Efficient Greedy Coordinate Descent for Composite Problems math.OC · 2018 · author #4
- Sparsified SGD with Memory cs.LG · 2018 · author #3
- COLA: Decentralized Linear Learning cs.DC · 2018 · author #3
- A Distributed Second-Order Algorithm You Can Trust cs.LG · 2018 · author #6
- Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients cs.LG · 2018 · author #3
- Training DNNs with Hybrid Block Floating Point cs.LG · 2018 · author #3
- On Matching Pursuit and Coordinate Descent stat.ML · 2018 · author #7
- Simple Unsupervised Keyphrase Extraction using Sentence Embeddings cs.CL · 2018 · author #5
- An Accelerated Communication-Efficient Primal-Dual Optimization Framework for Structured Machine Learning math.OC · 2017 · author #2
- Safe Adaptive Importance Sampling cs.LG · 2017 · author #3
- Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems cs.LG · 2017 · author #3
- Learning Aerial Image Segmentation from Online Maps cs.CV · 2017 · author #4
- Unsupervised robust nonparametric learning of hidden community properties stat.ML · 2017 · author #3
- Approximate Steepest Coordinate Descent cs.LG · 2017 · author #3
- Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees cs.LG · 2017 · author #4
- Generating Steganographic Text with LSTMs cs.AI · 2017 · author #2
- Faster Coordinate Descent via Adaptive Importance Sampling cs.LG · 2017 · author #3
- Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features cs.CL · 2017 · author #3
- Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification cs.CL · 2017 · author #8
- A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe cs.LG · 2017 · author #4
- CoCoA: A General Framework for Communication-Efficient Distributed Optimization cs.LG · 2016 · author #6
- Screening Rules for Convex Problems math.OC · 2016 · author #5
- Primal-Dual Rates and Certificates cs.LG · 2016 · author #4
- Pursuits in Structured Non-Convex Matrix Factorizations cs.LG · 2016 · author #3
- Distributed Optimization with Arbitrary Local Solvers cs.LG · 2015 · author #3
- L1-Regularized Distributed Optimization: A Communication-Efficient Primal-Dual Framework cs.LG · 2015 · author #4
- On the Global Linear Convergence of Frank-Wolfe Optimization Variants math.OC · 2015 · author #2
- Adding vs. Averaging in Distributed Primal-Dual Optimization cs.LG · 2015 · author #3
- Communication-Efficient Distributed Dual Coordinate Ascent cs.LG · 2014 · author #1
- An Affine Invariant Linear Convergence Analysis for Frank-Wolfe Algorithms math.OC · 2013 · author #2
- An Equivalence between the Lasso and Support Vector Machines cs.LG · 2013 · author #1
- An Optimal Affine Invariant Smooth Minimization Algorithm math.OC · 2013 · author #3
- Block-Coordinate Frank-Wolfe Optimization for Structural SVMs cs.LG · 2012 · author #2
- Convex Optimization without Projection Steps math.OC · 2011 · author #1
- A Combinatorial Algorithm to Compute Regularization Paths cs.LG · 2009 · author #3
- An Exponential Lower Bound on the Complexity of Regularization Paths cs.LG · 2009 · author #2
Mentions
- 1108.1170 #1 · arxiv_oai · confidence 0.70 Martin Jaggi
- 1502.03508 #3 · backfill · confidence 0.70 Martin Jaggi
- 2606.01128 #4 · arxiv_oai · confidence 0.70 Martin Jaggi
- 1409.1458 #1 · backfill · confidence 0.70 Martin Jaggi
- 1312.7864 #2 · backfill · confidence 0.70 Martin Jaggi
- 2605.29128 #3 · arxiv_oai · confidence 0.70 Martin Jaggi
- 1303.1152 #1 · backfill · confidence 0.70 Martin Jaggi
- 1301.0465 #3 · backfill · confidence 0.70 Martin Jaggi
- 1207.4747 #2 · backfill · confidence 0.70 Martin Jaggi
- 2311.16079 #19 · arxiv_oai · confidence 0.70 Martin Jaggi
- 1108.1170 #1 · backfill · confidence 0.70 Martin Jaggi
- 2510.15714 #2 · arxiv_oai · confidence 0.70 Martin Jaggi
- 0903.4856 #3 · backfill · confidence 0.70 Martin Jaggi
- 0903.4817 #2 · backfill · confidence 0.70 Martin Jaggi
Frequent Coauthors
- Sebastian U. Stich 8 shared papers
- Martin Tak\'a\v{c} 5 shared papers
- Michael I. Jordan 5 shared papers
- Sai Praneeth Karimireddy 5 shared papers
- Virginia Smith 5 shared papers
- Anant Raj 4 shared papers
- Chenxin Ma 4 shared papers
- Thomas Hofmann 4 shared papers
- Aurelien Lucchi 3 shared papers
- Bernd G\"artner 3 shared papers
- Celestine D\"unner 3 shared papers
- Francesco Locatello 3 shared papers
- Matteo Pagliardini 3 shared papers
- Michael Tschannen 3 shared papers
- Simone Forte 3 shared papers
- Simon Lacoste-Julien 3 shared papers
- Alejandro Hern\'andez Cano 2 shared papers
- Anastasia Koloskova 2 shared papers
- An Bian 2 shared papers
- Antoine Bosselut 2 shared papers