Peter Richtarik
where else to find them
no profile links on file
what they talk about
all 4 in the filters
where they keep going back
no series more than once — all 5 in the filters
on a stage with
- Amedeo Sapioonce
- Arvind Krishnamurthyonce
- Changhoon Kimonce
all 9 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| From the Ball-proximal (Broximal) Point Method to Efficient Training of LLM | Learning from Heterogeneous Sources 2026 | 2026-02-23 |
Proposes the Ball-Proximal (Broximal) Point Method as a ball-constrained analogue of proximal methods and proves surprising guarantees: linear convergence and… | ||
| Tutorial: Federated Optimization, Part I | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
Overview of concrete results: the lecture compares cost models (notably the communication-to-server-only cost model), analyzes DCGD with unbiased compressors… | ||
| Tutorial: Federated Optimization, Part II | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
DIANA removes the interpolation assumption by compressing gradient differences, yields near‑linear convergence without shared optimizers, and can be… | ||
| Tutorial: Federated Optimization, Part III | Federated and Collaborative Learning Boot Camp 2026 | 2026-01-26 |
ProxSkip connects compression plus EF21 to acceleration through local training and links to proximal-point lineage (DANE, Axfeldt, double stabilization) while… | ||
| Scaling Distributed Machine Learning with In-Network Aggregation | NSDI ’21 | 2021-04-12 |
Implements SwitchML: a co-designed system that pushes aggregation into a programmable switch dataplane to reduce model-update volume and offload the all-reduce… | ||
| Stochastic Quasi-Gradient Methods: Variance Reduction via Jacobian Sketching | Randomized Numerical Linear Algebra and Applications 2018 | 2018-09-24 |
Introduces JacSketch, a variance-reduced stochastic optimizer that maintains cheap, sketched estimates of the full Jacobian and uses a sketch-and-project… | ||
| Parallel Coordinate Descent Methods for Big Data Optimization | Parallel and Distributed Algorithms for Inference and Optimization (Simons Institute, Oct. 21–24, 2013) | 2013-10-21 |
Presents a concrete parallel coordinate-descent framework built around an ESO (expected separable over-approximation) that produces algorithm parameters beta… | ||
| nothing matches | ||