Machine-learning-nederland June 2023

machine-learning-nederland@list.uva.nl

3 participants
4 discussions

Stats and ML Thematic seminar: Nikita Zhivotovskiy, Friday July 7, 15h00
by Tim van Erven 26 Jun '23

26 Jun '23

Dear all, On Friday July 7 we have Nikita Zhivotovskiy speaking in the Statistics and Machine Learning Thematic Seminar. Nikita will be visiting us July 3-7. He has done excellent work both in statistics and machine learning, so it is highly recommended to come meet him. *Nikita Zhivotovskiy *(UC Berkeley, Department of Statistics, https://sites.google.com/view/nikitazhivotovskiy/) *Friday July 7*, 15h00-16h00 In person, at the University of Amsterdam Location: Science Park 904, Room A1.04 *Sharper Risk Bounds for Statistical Aggregation *In this talk, we take a fresh look at the classical results in the theory of statistical aggregation, focusing on the transition from global complexity to a more manageable local one. The goal of aggregation is to combine several base predictors to achieve a prediction nearly as accurate as the best one. This flexible approach operates without any assumptions on the structure of the class or the nature of the target. Though aggregation is studied in both sequential and statistical settings, each with their unique differences, they both traditionally use the same "global" complexity measure. Our discussion will highlight the lesser-known PAC-Bayes localization method used in our proofs, allowing us to prove a localized version of a classical bound for the exponential weights estimator by Leung and Barron, and a deviation-optimal localized bound for the Q-aggregation estimator. Furthermore, we will explore the links between our work and ridge regression. Joint work with Jaouad Mourtada and Tomas Vaškevičius. * * Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

June 21, 15:00 Machine Learning Theory Seminar++ Meeting with Alexander Ly
by Wouter Koolen-Wijkstra 17 Jun '23

17 Jun '23

Dear researchers, Centrum Wiskunde & Informatica (CWI) kindly invites you to the eight Seminar++ meeting on Machine Learning Theory, taking place on Wednesday June 21 from 15:00 - 17:00. These Seminar++ meetings consist of a one-hour lecture building up to an open problem, followed by an hour of brainstorming time. The meeting is intended for interested researchers including PhD students. These meetings are freely accessible without registration. Cookies, coffee and tea will be provided in the half-time break. The meeting of 21 June will be hosted by: Alexander Ly <https://www.alexander-ly.com/>, Postdoc at the Centrum Wiskunde & Informatica <https://www.cwi.nl/>. On constructing e-values for statistical practice *Abstract:* The safe anytime-valid inference framework based on e-values allows practitioners to adaptively design their experiments and draw more reliable conclusions compared to conventional p-value-based approaches. The presentation begins with a concise overview of the recently developed general theory of e-values and the various procedures to construct them. In order to distinguish among the different e-values, Grünwald, de Heide and Koolen (2019) introduced the GROW criterion along with a general procedure specifically designed to construct the optimal e-value according to this criterion. Practical considerations and the context of the statistical problem itself might lead us to deviate from recommending this so-called GROW e-value. We shed light on the choices we made when constructing e-values for fundamental classical inference problems, such as z-tests, t-tests, one-way ANOVAs, and (generalised) linear models. Our objective is to investigate the potential generalisability of these context-specific solutions to a broader range of inference problems in hope to expand the practicality and versatility of safe anytime-valid inference. The event takes place in room L016 in the CWI building, Science Park 123, Amsterdam. The Seminar++ Meetings are part of the Machine Learning Theory Semester Programme <https://www.cwi.nl/en/events/cwi-research-semester-programs/research-progra…>, which runs in Spring 2023. Best regards on behalf of CWI from the program committee, Wouter Koolen

1 0

CfP 7th Interactive Adaptive Learning Workshop @ ECML PKDD 2023 (September, Torino)
by Krempl, G.M. (Georg) 06 Jun '23

06 Jun '23

We organize the 7th international workshop on Interactive Adaptive Learning, to be held at ECML PKDD 2023 on September 22nd in Torino, Italy: Interactive Adaptive Learning Workshop @ ECML PKDD link : https://www.activeml.net/ial2023/ Key dates (Anytime-on-Earth): Abstract Registration: Monday, June 12th 2023 Paper Submission: Wednesday, June 21st 2023 Notification: Monday, July 24th 2023 Camera Ready: Sunday, August 13th 2023 Workshop & Tutorial: Friday, September 22nd, 2021, Torino, Italy Topics of interest include: Novel Techniques for Active, Semi-Supervised, Transfer, or Weakly Supervised Learning Innovative Use and Applications of Active, Semi-Supervised, Transfer, or Weakly Supervised Learning Techniques for Combined Interactive Adaptive Learning We welcome submissions of original regular (8-16 pages) and short papers/extended abstracts (2-4 pages). Each submission will be double-blind peer-reviewed; accepted papers will be published at ceur-ws.org, which is indexed, e.g., by Google Scholar, DBLP, Scopus, and will be presented & discussed at the workshop. For short papers, works-in-progress, open challenges in research or industrial applications that initiate discussions and collaborations are welcome. Please format your papers according to the CEUR-WS format and submit them via EasyChair: https://easychair.org/conferences/?conf=ial2023 We look forward to your contributions and participation at the workshop, the organisers, Mirko Bunse, Barbara Hammer, Georg Krempl, Vincent Lemaire, Alaa Othman, and Amal Saadallah.

1 0

Stats and ML Thematic seminar: Nikita Zhivotovskiy, Friday July 7, 15h00
by Tim van Erven 05 Jun '23

05 Jun '23

Dear all, On Friday July 7 we have Nikita Zhivotovskiy speaking in the Statistics and Machine Learning Thematic Seminar. Nikita will be visiting us July 3-7. He has done excellent work both in statistics and machine learning, so it is highly recommended to come meet him. *Nikita Zhivotovskiy *(UC Berkeley, Department of Statistics, https://sites.google.com/view/nikitazhivotovskiy/) *Friday July 7*, 15h00-16h00 In person, at the University of Amsterdam Location: Science Park 904, Room TBA *Sharper Risk Bounds for Statistical Aggregation *In this talk, we take a fresh look at the classical results in the theory of statistical aggregation, focusing on the transition from global complexity to a more manageable local one. The goal of aggregation is to combine several base predictors to achieve a prediction nearly as accurate as the best one. This flexible approach operates without any assumptions on the structure of the class or the nature of the target. Though aggregation is studied in both sequential and statistical settings, each with their unique differences, they both traditionally use the same "global" complexity measure. Our discussion will highlight the lesser-known PAC-Bayes localization method used in our proofs, allowing us to prove a localized version of a classical bound for the exponential weights estimator by Leung and Barron, and a deviation-optimal localized bound for the Q-aggregation estimator. Furthermore, we will explore the links between our work and ridge regression. Joint work with Jaouad Mourtada and Tomas Vaškevičius. * * Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

2024

2023

2022

2021

2020

Machine-learning-nederland June 2023