Events
retrieve:
Return the details about the given Memento id.
list:
List all Memento objects.
GET /api/v1/mementos/288/events/?format=api&ordering=fr_name
{ "count": 2, "next": null, "previous": null, "results": [ { "id": 71903, "title": "Computer-aided proofs in first-order optimization, with applications to error feedback", "slug": "computer-aided-proofs-in-first-order-optimization", "event_url": "https://memento.epfl.ch/event/computer-aided-proofs-in-first-order-optimization", "visual_url": "https://memento.epfl.ch/image/33221/200x112.jpg", "visual_large_url": "https://memento.epfl.ch/image/33221/720x405.jpg", "visual_maxsize_url": "https://memento.epfl.ch/image/33221/max-size.jpg", "lang": "en", "start_date": "2026-05-29", "end_date": "2026-05-29", "start_time": "15:15:00", "end_time": "16:15:00", "description": "<p>First-order methods are widely used in optimization and machine learning, and their behavior is often analyzed through the spectrum of worst case convergence rates. Obtaining such guarantees is often difficult and both time consuming and error-prone. Starting with the work of Drori and Teboulle (2014), novel techniques have been used to gain numerical insights, leading to the release of various performance estimation (PE) software. <br>\r\n<br>\r\nIn this talk, I will show how various computer-aided techniques can be used to study first-order optimization methods in a systematic way. From performance estimation problems with automated Lyapunov discovery, to symbolic regression and computer algebra systems, novel tools completely reshape the way we approach theory of optimization. <br>\r\nAs a main example, I will focus on error feedback methods used with compressed communication in distributed optimization. While error feedback has been widely studied, existing theory often provides untight (thus unreliable) bounds. I will present tight analyses with matching lower bounds that allow a fair comparison between error feedback schemes and standard compressed gradient descent, and help explain when error feedback is useful and when it is not.<br>\r\n<br>\r\nOverall, the talk aims to show how various computer-aided proofs can lead to clearer and more reliable insights into first-order optimization methods.<br>\r\n<br>\r\nBased on :<br>\r\n<a href=\"https://icml.cc/virtual/2026/poster/62713\" target=\"_blank\">A Tight Theory of Error Feedback Algorithms in Distributed Optimization,</a> DB Thomsen, A Taylor, A Dieuleveut<br>\r\nInternational Conference on Machine Learning (ICML 2026)<br>\r\n<a href=\"https://scholar.google.com/citations?view_op=view_citation&hl=fr&user=ge-OinUAAAAJ&sortby=pubdate&citation_for_view=ge-OinUAAAAJ:q3oQSFYPqjQC\" target=\"_blank\">Tight analyses of first-order methods with error feedback</a>, DB Thomsen, A Taylor, A Dieuleveut<br>\r\nAdvances in Neural Information Processing Systems (NeurIPS) (2025).<br>\r\n<a href=\"https://scholar.google.com/citations?view_op=view_citation&hl=fr&user=ge-OinUAAAAJ&sortby=pubdate&citation_for_view=ge-OinUAAAAJ:L8Ckcad2t8MC\" target=\"_blank\">PEPit: computer-assisted worst-case analyses of first-order optimization methods in Python</a><br>\r\nB Goujaud, C Moucer, F Glineur, JM Hendrickx, AB Taylor, A Dieuleveut<br>\r\nMathematical Programming Computation 16 (3), 337-367 (2024)<br>\r\n(eventually - as a detour) <a href=\"https://scholar.google.com/citations?view_op=view_citation&hl=fr&user=ge-OinUAAAAJ&sortby=pubdate&citation_for_view=ge-OinUAAAAJ:wbdj-CoPYUoC\" target=\"_blank\">Provable non-accelerations of the heavy-ball method</a> B Goujaud, A Taylor, A Dieuleveut, Mathematical Programming, 1-59 (2025)<br>\r\n </p>", "image_description": "", "creation_date": "2026-05-19T09:20:45", "last_modification_date": "2026-05-19T09:22:37", "link_label": "", "link_url": "https://www.epfl.ch/schools/sb/research/math/research/statistics/", "canceled": "False", "cancel_reason": "", "place_and_room": "CM 1 517", "url_place_and_room": "https://plan.epfl.ch/?room==CM%201%20517", "url_online_room": "", "spoken_languages": [ "https://memento.epfl.ch/api/v1/spoken_languages/2/?format=api" ], "speaker": "Aymeric Dieuleveut, Ecole Polytechnique, Institut Polytechnique de Paris", "organizer": "Myrto Limnios ", "contact": "Maroussia Schaffner", "is_internal": "False", "theme": "", "vulgarization": { "id": 2, "fr_label": "Public averti", "en_label": "Informed public" }, "registration": { "id": 3, "fr_label": "Entrée libre", "en_label": "Free" }, "keywords": "", "file": null, "icalendar_url": "https://memento.epfl.ch/event/export/120800/", "category": { "id": 1, "code": "CONF", "fr_label": "Conférences - Séminaires", "en_label": "Conferences - Seminars", "activated": true }, "academic_calendar_category": null, "domains": [], "mementos": [ "https://memento.epfl.ch/api/v1/mementos/5/?format=api", "https://memento.epfl.ch/api/v1/mementos/7/?format=api", "https://memento.epfl.ch/api/v1/mementos/288/?format=api" ] }, { "id": 70824, "title": "MoRAT: Mathematics of Randomized linear Algebra Techniques - Summer School 2026", "slug": "morat-mathematics-of-randomized-linear-algebra-t-2", "event_url": "https://memento.epfl.ch/event/morat-mathematics-of-randomized-linear-algebra-t-2", "visual_url": "https://memento.epfl.ch/image/32231/200x112.jpg", "visual_large_url": "https://memento.epfl.ch/image/32231/720x405.jpg", "visual_maxsize_url": "https://memento.epfl.ch/image/32231/max-size.jpg", "lang": "en", "start_date": "2026-08-31", "end_date": "2026-09-04", "start_time": "10:00:00", "end_time": "12:00:00", "description": "<p>This summer school, organized by seven PhD students from EPFL and ETH Zurich, brings together leading researchers and postgraduate students. Participants will learn modern mathematical and probabilistic methods for linear algebra through lectures by experts in randomized numerical linear algebra. The program also includes networking opportunities with fellow participants, lecturers, and industry representatives.<br>\r\n<br>\r\nThe summer school takes place in a modern hotel in the middle of the historic lakeside town of Murten/Morat. Accommodation, food, and all other costs during the summer school will be covered. All participants are charged a small registration fee.<br>\r\n<br>\r\n<a href=\"http://morat2026.epfl.ch/registration\">Registrations</a> can be made until February 15 and are primarily open to doctoral students from the ETH domain, with limited exceptions for international and master’s students. It is possible to obtain 2 ECTS credits for attending MoRAT.</p>", "image_description": "", "creation_date": "2026-01-09T14:57:01", "last_modification_date": "2026-01-09T17:11:09", "link_label": "morat2026.epfl.ch", "link_url": "https://morat2026.epfl.ch/", "canceled": "False", "cancel_reason": "", "place_and_room": "Hotel Murtenhof & Krone", "url_place_and_room": "", "url_online_room": "", "spoken_languages": [ "https://memento.epfl.ch/api/v1/spoken_languages/2/?format=api" ], "speaker": "Daniel Kressner (EPFL), Laura Grigori (EPFL/PSI), Alice Cortinovis (Università di Pisa), Afonso S. Bandeira (ETH Zurich), Yuji Nakatsukasa (Oxford), Hussam al Daas (Rutherford Appleton Laboratory)", "organizer": "<a href=\"http://morat2026.epfl.ch/organisers\">morat2026.epfl.ch/organisers</a>", "contact": "<a href=\"mailto:[email protected]\">[email protected]</a>", "is_internal": "False", "theme": "", "vulgarization": { "id": 1, "fr_label": "Tout public", "en_label": "General public" }, "registration": { "id": 1, "fr_label": "Sur inscription", "en_label": "Registration required" }, "keywords": "randomized numerical linear algebra, randomized algorithms, numerical analysis", "file": null, "icalendar_url": "https://memento.epfl.ch/event/export/119255/", "category": { "id": 1, "code": "CONF", "fr_label": "Conférences - Séminaires", "en_label": "Conferences - Seminars", "activated": true }, "academic_calendar_category": null, "domains": [], "mementos": [ "https://memento.epfl.ch/api/v1/mementos/5/?format=api", "https://memento.epfl.ch/api/v1/mementos/6/?format=api", "https://memento.epfl.ch/api/v1/mementos/7/?format=api", "https://memento.epfl.ch/api/v1/mementos/27/?format=api", "https://memento.epfl.ch/api/v1/mementos/246/?format=api", "https://memento.epfl.ch/api/v1/mementos/288/?format=api", "https://memento.epfl.ch/api/v1/mementos/318/?format=api" ] } ] }
