Sebastian U. Stich

发表

Safe Adaptive Importance Sampling

Martin Jaggi, Sebastian U. Stich, Anant Raj, 2017, NIPS.

Convex Optimization with Random Pursuit

Sebastian U. Stich, S. Stich, 2014 .

Unified Optimal Analysis of the (Stochastic) Gradient Method pdf

Sebastian U. Stich, S. Stich, 2019, ArXiv.

Dynamic Model Pruning with Feedback pdf

Martin Jaggi, Luis Barba, Tao Lin, 2020, ICLR.

Decentralized Deep Learning with Arbitrary Communication Compression pdf

Martin Jaggi, Tao Lin, Sebastian U. Stich, 2019, ICLR.

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! pdf

Martin Jaggi, Sebastian U. Stich, Anastasia Koloskova, 2020, AISTATS.

Is Local SGD Better than Minibatch SGD? pdf

Ohad Shamir, Nathan Srebro, Sebastian U. Stich, 2020, ICML.

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization pdf

Robert M. Gower, Peter Richtárik, Sebastian U. Stich, 2018, NeurIPS.

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

Tao Lin, Martin Jaggi, Sebastian U. Stich, 2018, ICLR.

Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication

Martin Jaggi, Sebastian U. Stich, Anastasia Koloskova, 2019, ICML.

Approximate Steepest Coordinate Descent pdf

Martin Jaggi, Sebastian U. Stich, Anant Raj, 2017, ICML.

Advances and Open Problems in Federated Learning pdf

Richard Nock, Zaïd Harchaoui, David Evans, 2019, Found. Trends Mach. Learn..

k-SVRG: Variance Reduction for Large Scale Optimization

Sebastian U. Stich, Anant Raj, Anant Raj, 2018, 1805.00982.

Error Feedback Fixes SignSGD and other Gradient Compression Schemes pdf

Martin Jaggi, Sebastian U. Stich, Quentin Rebjock, 2019, ICML.

Sparsified SGD with Memory

Martin Jaggi, Sebastian U. Stich, Jean-Baptiste Cordonnier, 2018, NeurIPS.

Efficiency of the Accelerated Coordinate Descent Method on Structured Optimization Problems

Yurii Nesterov, Sebastian U. Stich, Y. Nesterov, 2017, SIAM J. Optim..

Extrapolation for Large-batch Training in Deep Learning pdf

Martin Jaggi, Sebastian U. Stich, Tao Lin, 2020, ICML.

On Matching Pursuit and Coordinate Descent

Gunnar Rätsch, Bernhard Schölkopf, Martin Jaggi, 2018, ICML 2018.

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

Martin Jaggi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2018, AISTATS.

On Low Complexity Acceleration Techniques for Randomized Optimization

Sebastian U. Stich, S. Stich, 2014, PPSN.

On Communication Compression for Distributed Optimization on Heterogeneous Data pdf

Sebastian U. Stich, S. Stich, 2020, ArXiv.

SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning pdf

Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, 2019, ArXiv.

Variable metric random pursuit

Christian L. Müller, Sebastian U. Stich, Bernd Gärtner, 2012, Math. Program..

Optimization of Convex Functions with Random Pursuit pdf

Christian L. Müller, Sebastian U. Stich, Bernd Gärtner, 2011, SIAM J. Optim..

On Two Continuum Armed Bandit Problems in High Dimensions

Sebastian U. Stich, Hemant Tyagi, Bernd Gärtner, 2014, Theory of Computing Systems.

On Two Problems Regarding the Hamiltonian Cycle Game

Sebastian U. Stich, Dan Hefetz, Dan Hefetz, 2009, Electron. J. Comb..

The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication pdf

Sebastian U. Stich, Sai Praneeth Karimireddy, 2019, ArXiv.

Analysis of SGD with Biased Gradient Estimators pdf

Sebastian U. Stich, Ahmad Ajalloeian, Ahmad Ajalloeian, 2020, ArXiv.

SVRG meets SAGA: k-SVRG - A Tale of Limited Memory pdf

Sebastian U. Stich, Anant Raj, Anant Raj, 2018, ArXiv.

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning.

Martin Jaggi, Sashank J. Reddi, Sebastian U. Stich, 2020, 2008.03606.

Stochastic continuum armed bandit problem of few linear parameters in high dimensions pdf

Sebastian U. Stich, Hemant Tyagi, Bernd Gärtner, 2013, ArXiv.

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

Martin Jaggi, Sebastian U. Stich, Nicolas Loizou, 2020, ICML.

Taming GANs with Lookahead-Minmax

Tatjana Chavdarova, Matteo Pagliardini, Martin Jaggi, 2020 .

On Spectral Invariance of Randomized Hessian and Covariance Matrix Adaptation Schemes

Christian L. Müller, Sebastian U. Stich, C. Müller, 2012, PPSN.

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

Martin Jaggi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2018, ArXiv.

Local SGD Converges Fast and Communicates Little pdf

Sebastian U. Stich, S. Stich, 2018, ICLR.

On the existence of ordinary triangles

József Solymosi, Márton Naszódi, Sebastian U. Stich, 2017, Comput. Geom..

SCAFFOLD: Stochastic Controlled Averaging for Federated Learning

Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh, 2019, ICML.

Efficient Greedy Coordinate Descent for Composite Problems

Martin Jaggi, Sebastian U. Stich, Anastasia Koloskova, 2019, AISTATS.

Stochastic Variance Reduced Gradient Optimization of Generative Adversarial Networks

Tatjana Chavdarova, Martin Jaggi, Sebastian U. Stich, 2018, ICML 2018.

On Matching Pursuit and Coordinate Descent

Gunnar Rätsch, Bernhard Schölkopf, Martin Jaggi, 2018, ICML.

Advances and Open Problems in Federated Learning

Richard Nock, Zaïd Harchaoui, Mehdi Bennis, 2021, Found. Trends Mach. Learn..

On Second-order Optimization Methods for Federated Learning pdf

Martin Jaggi, Sebastian U. Stich, Stephan Gunnemann, 2021, ArXiv.

Linear Speedup in Personalized Collaborative Learning pdf

Martin Jaggi, Sebastian U. Stich, Nicolas Flammarion, 2021, ArXiv.

LENA: Communication-Efficient Distributed Learning with Self-Triggered Gradient Uploads

Martin Jaggi, Hossein Shokri Ghadikolaei, Sebastian U. Stich, 2021, AISTATS.

A Field Guide to Federated Optimization pdf

Suhas Diggavi, Ameet Talwalkar, Tara Javidi, 2021, ArXiv.

Consensus Control for Decentralized Deep Learning pdf

Martin Jaggi, Sebastian U. Stich, Anastasia Koloskova, 2021, ICML.

Masked Training of Neural Networks with Partial Gradients

Martin Jaggi, Sebastian U. Stich, Amirkeivan Mohtashami, 2021 .

Taming GANs with Lookahead-Minmax

Tatjana Chavdarova, Matteo Pagliardini, Martin Jaggi, 2020, ICLR.

Tatjana Chavdarova, Matteo Pagliardini, Sebastian U. Stich, 2021, ArXiv.

Simultaneous Training of Partially Masked Neural Networks pdf

Martin Jaggi, Sebastian U. Stich, Amirkeivan Mohtashami, 2021, ArXiv.

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training pdf

Mario Fritz, Sebastian U. Stich, Yang He, 2021, ArXiv.

Semantic Perturbations with Normalizing Flows for Improved Generalization pdf

Tatjana Chavdarova, Martin Jaggi, Sebastian U. Stich, 2021, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Martin Jaggi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2021, ICML.

RelaySum for Decentralized Deep Learning on Heterogeneous Data pdf

Martin Jaggi, Sebastian U. Stich, Thijs Vogels, 2021, ArXiv.

Convergence of Local Search

Sebastian U. Stich, G. Bernd, 2011 .

Ensemble Distillation for Robust Model Fusion in Federated Learning

Sebastian U. Stich, Martin Jaggi, Tao Lin, 2020, NeurIPS.

An Improved Analysis of Gradient Tracking for Decentralized Machine Learning

Sebastian U. Stich, Anastasia Koloskova, Tao Lin, 2022, NeurIPS.

SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning

Sashank J. Reddi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2019, ArXiv.

The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication

Sebastian U. Stich, Sai Praneeth Karimireddy, S. Stich, 2019, 1909.05350.

Breaking the centralized barrier for cross-device federated learning

Sashank J. Reddi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2021, NeurIPS.

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning.

Martin Jaggi, Mehryar Mohri, Sashank J. Reddi, 2020, 2008.03606.

On the Convergence of SGD with Biased Gradients

Sebastian U. Stich, Ahmad Ajalloeian, Ahmad Ajalloeian, 2020, 2008.00051.

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

Martin Jaggi, Sebastian U. Stich, Nicolas Loizou, 2020, ICML.

Is Local SGD Better than Minibatch SGD? pdf

Ohad Shamir, Nathan Srebro, Sebastian U. Stich, 2020, ICML.

Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning

Sashank J. Reddi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2020, ArXiv.

Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning

Sebastian U. Stich, Martin Jaggi, Anastasia Koloskova, 2022, Neural Information Processing Systems.

Stochastic Distributed Learning with Gradient Quantization and Variance Reduction

Sebastian U. Stich, Peter Richtárik, Konstantin Mishchenko, 2019, 1904.05115.

On Avoiding Local Minima Using Gradient Descent With Large Learning Rates

Sebastian U. Stich, Martin Jaggi, Amirkeivan Mohtashami, 2022, arXiv.org.

Stochastic distributed learning with gradient quantization and double-variance reduction

Sebastian U. Stich, Peter Richtárik, Konstantin Mishchenko, 2022, Optim. Methods Softw..

Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning

Sebastian U. Stich, Martin Jaggi, Anastasia Koloskova, 2022, NeurIPS.

SCAFFOLD: Stochastic Controlled Averaging for Federated Learning

Sashank J. Reddi, Sebastian U. Stich, Sai Praneeth Karimireddy, 2019, ICML.

RelaySum for Decentralized Deep Learning on Heterogeneous Data

Sebastian U. Stich, Sai Praneeth Karimireddy, Thijs Vogels, 2021, NeurIPS.

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates

Sebastian U. Stich, Nicolas Loizou, Siqi Zhang, 2023, ArXiv.

On the Effectiveness of Partial Variance Reduction in Federated Learning with Heterogeneous Data

Sebastian U. Stich, T. S. Alstrøm, Bo Li, 2023, Computer Vision and Pattern Recognition.

Linear Speedup in Personalized Collaborative Learning

Sebastian U. Stich, Sai Praneeth Karimireddy, El Mahdi Chayti, 2021, ArXiv.

Masked Training of Neural Networks with Partial Gradients

Sebastian U. Stich, Martin Jaggi, Amirkeivan Mohtashami, 2021, AISTATS.

ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!

Sebastian U. Stich, Konstantin Mishchenko, Grigory Malinovsky, 2022, ICML.

The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication

Sebastian U. Stich, Sai Praneeth Karimireddy, S. Stich, 2019, ArXiv.

Decentralized Gradient Tracking with Local Steps

Sebastian U. Stich, Anastasia Koloskova, Tao Lin, 2023, Optimization Methods and Software.

Decentralized Local Stochastic Extra-Gradient for Variational Inequalities

Sebastian U. Stich, P. Dvurechensky, A. Gasnikov, 2021, NeurIPS.

Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees

Sebastian U. Stich, Anastasia Koloskova, Hadrien Hendrikx, 2023, ICML.

Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction

Sebastian U. Stich, Xiao-Yan Jiang, 2023, NeurIPS.

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training

Sebastian U. Stich, Mario Fritz, Hui-Po Wang, 2021, ICML.

Data-heterogeneity-aware Mixing for Decentralized Learning

Sebastian U. Stich, Martin Jaggi, Anastasia Koloskova, 2022, ArXiv.

Consensus Control for Decentralized Deep Learning

Sebastian U. Stich, Martin Jaggi, Anastasia Koloskova, 2021, ICML.