- Machine-learning-nederland

May 10, 15:00 Machine Learning Theory Seminar++ Meeting with Rianne de Heide
by Wouter Koolen-Wijkstra 20 Apr '23

20 Apr '23

Dear researchers, Centrum Wiskunde & Informatica (CWI) kindly invites you to the fifth Seminar++ meeting on Machine Learning Theory, taking place on Wednesday May 10 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 10 May will be hosted by: Rianne de Heide <https://riannedeheide.github.io/> (Assistant Professor at the Vrije Universiteit Amsterdam <https://vu.nl/>) *Multiple testing with e-values: overview and open problems* Abstract: Researchers in genomics and neuroimaging often perform hundreds of thousands of hypothesis tests simultaneously. The scale of these multiple hypothesis testing problems is enormous, and with extreme dimensionality comes extreme risk for false positives. The field of multiple testing addresses this problem in various ways. Recently, the new theory of hypothesis testing with e-values has been brought to the field of multiple testing. In this talk I will give an overview of the most important frameworks in multiple testing and recent developments in multiple testing with e-values. Finally, I will open the discussion for open problems in this area, focusing on FDP estimation and confidence with e-values. This will create a framework for fully interactive multiple testing. 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

April 19, 15:00: Machine Learning Theory Seminar++ Meeting with Dirk van der Hoeven
by Wouter Koolen-Wijkstra 14 Apr '23

14 Apr '23

Dear researchers, Centrum Wiskunde & Informatica (CWI) kindly invites you to the fourth Seminar++ meeting on Machine Learning Theory, taking place on Wednesday April 19 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 19 April will be hosted by: Dirk van der Hoeven <http://dirkvanderhoeven.com/about> (Postdoc at the University of Amsterdam <https://www.uva.nl/>) High-Probability Risk Bounds via Sequential Predictors *Abstract:* Online learning methods yield sequential regret bounds under minimal assumptions and provide in-expectation results in statistical learning. However, despite the seeming advantage of online guarantees over their statistical counterparts, recent findings indicate that in many important cases, regret bounds may not guarantee high probability risk bounds. In this work we show that online to batch conversions applied to general online learning algorithms are more powerful than previously thought. Via a new second-order correction to the loss function, we obtain sharp high-probability risk bounds for many classical statistical problems, such as model selection aggregation, linear regression, logistic regression, and—more generally—conditional density estimation. Our analysis relies on the fact that many online learning algorithms are improper, as they are not restricted to use predictors from a given reference class. The improper nature enables significant improvements in the dependencies on various problem parameters. In the context of statistical aggregation of finite families, we provide a simple estimator achieving the optimal rate of aggregation in the model selection aggregation setup with general exp-concave losses. *First open problem:* This open problem will be the main focus of the seminar. The result for logistic regression is nearly optimal and the algorithm is computationally efficient in the sense that the runtime is polynomial in the relevant problem parameters. However, it is a polynomial with a very high degree, making the algorithm practically not very useful for reasonable problem parameters. For in expectation guarantees it is known how to reduce the runtime to /d^2 T/ at the cost of a slightly worse excess risk bound, where /d/ is the dimension of the problem and /T/ is the number of datapoints. Unfortunately it is not immediately clear how to use the ideas from the faster algorithm to obtain a high-probability excess risk bound with a /d^2 T/ runtime algorithm. This open problem asks for the following: can we obtain a reasonable excess risk bound with high-probability in /d^2 T/ runtime for logistic regression. *Second open problem:* Our results heavily rely on a particular inequality for exp-concave losses. I would like to extend our ideas to a different class of loss function, namely self-concordant loss functions. Given previous results in statistical learning literature (see https://arxiv.org/pdf/2105.08866.pdf), I expect this to be possible. 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/~wmkoolen/MLT_Sem23/index.html>, which runs in Spring 2023. Best regards on behalf of CWI from the program committee, Wouter Koolen

1 0

April 12 Afternoon: Lectures on Machine Learning Theory by Peters and Lattimore
by Wouter Koolen-Wijkstra 07 Apr '23

07 Apr '23

Dear colleagues, Centrum Wiskunde & Informatica (CWI) kindly invites you to a lecture afternoon focused on theory of machine learning, with two distinguished speakers that will focus on philosophical and technical challenges in learning to model and explore the unknown environment. The program on 12 April: 14.00 Jonas Peters <http://web.math.ku.dk/~peters/> (University of Copenhagen): /Recent Advances in Causal Inference/ 15.00 Break 15.30 Tor Lattimore <https://tor-lattimore.com/> (DeepMind): /The Curse and Blessing of Curvature for Zeroth-order Convex Optimisation/ 16.30 Reception The first talk will be delivered remotely, the second live. For further details, please check the abstracts below and the website <https://www.cwi.nl/en/events/cwi-research-semester-programs/mid-semester-le…>. These research-level lectures are intended for a non-specialist audience, and are freely accessible. The event takes place in the Amsterdam Science Park Congress Centre. This "Mid Semester Lecture", marks the half-way point of the Machine Learning Theory Semester Programme <https://www.cwi.nl/en/events/cwi-research-semester-programs/research-progra…>, which runs in Spring 2023. Researchers in Machine Learning Theory may also be interested in the ongoing Seminar++ meetings <https://www.cwi.nl/en/events/cwi-research-semester-programs/seminar-part-4-…> every other Wednesday. Best regards on behalf of CWI from the program committee, Wouter Koolen Tor Lattimore /The Curse and Blessing of Curvature for Zeroth-order Convex Optimisation/ *Abstract:* Zeroth-order convex optimisation is still quite poorly understood. I will tell a story about how to use gradient-based methods without access to gradients and explain how curvature of the loss function plays the roles of both devil and angel. The main result is a near-optimal sample-complexity analysis of a simple and computationally efficient second-order method applied to a quadratic surrogate loss. The talk is based on a recent paper <https://arxiv.org/abs/2302.05371> with András György. Jonas Peters/ Recent Advances in Causal Inference/ *Abstract:* see website <https://www.cwi.nl/en/events/cwi-research-semester-programs/mid-semester-le…>

1 0

[Machines] (IF: 2.899, ISSN: 2075-1702) — Special Issue "Machine Learning in Autonomous Driving"-Call for Paper
by Wilda.Wang 28 Mar '23

28 Mar '23

To Whom It May Concern: This is Wilda from the MDPI Machines Editorial Office, and I'm submitting a mailing list request. I would greatly appreciate it if you could assist me in sending out the following message. Please do not hesitate to contact me if you have any questions or if something needs to be revised. Thank you once more! ----------------------------------------------- Dear Colleagues, Greetings from Machines, MDPI! We are getting in touch to ask whether you plan on submitting work in the Special Issue "Machine Learning in Autonomous Driving", which is edited by Prof. Dr. Young-guk Ha of Konkuk University. SI Link: https://www.mdpi.com/journal/machines/special_issues/HN1P17643G The aim of this Special Issue is to present recent advances and challenges in the application of machine learning technology in autonomous driving, including in driving data preparation, object detection, trajectory prediction, driving situation awareness, vehicle localization, driving action planning, and vehicle control. This would be a good opportunity to gather researchers in developing machine learning models and algorithms for autonomous driving to discuss and share original research works and practical experiences. If you have any questions, please feel free to contact me. Expect your reply at your first convenience. Kind regards, Wilda Wang Disclaimer: MDPI recognizes the importance of data privacy and protection. We treat personal data in line with the General Data Protection Regulation (GDPR) and with what the community expects of us. The information contained in this message is confidential and intended solely for the use of the individual or entity to whom they are addressed. If you have received this message in error, please notify me and delete this message from your system. You may not copy this message in its entirety or in part, or disclose its contents to anyone.

1 0

April 5, 15:00: Machine Learning Theory Seminar++ Meeting with Patrick Forré
by Wouter Koolen-Wijkstra 26 Mar '23

26 Mar '23

Dear researchers, Centrum Wiskunde & Informatica (CWI) kindly invites you to the third Seminar++ meeting on Machine Learning Theory, taking place on Wednesday April 5 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 5 April will be hosted by: Patrick Forré <http://amlab.science.uva.nl/people/PatrickForre/> (Assistant professor at the University of Amsterdam <https://www.uva.nl/>) A convenient foundation of probability theory for probabilistic programming, graphical models, causality and statistics *Abstract:* Random functions and functions whose outputs are random functions arise in many areas of statistics, probability theory and computer science, like probabilistic graphical models, causality, the area of conditional independence, probabilistic programming, etc. Despite their frequent appearances the usual measure-theoretic foundations of probability theory are not capable of properly describing such random functions. To avoid typical work-arounds, which often come with inconvenient restrictions, in this talk, we describe how one can instead fix the foundations of probability theory by introducing ‘quasi-measurable spaces’, which then replace the role of measurable spaces. We then demonstrate how the mentioned problems are solved in this framework and further other convenient properties. Furthermore, we show how one can rigorously express probabilistic graphical models and typical causal assumptions using quasi-measurable spaces. 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/~wmkoolen/MLT_Sem23/index.html>, which runs in Spring 2023. Best regards on behalf of CWI from the program committee, Wouter Koolen

1 0

Senior researcher position in reinforcement learning
by Marcel van Gerven 20 Mar '23

20 Mar '23

The AI Department of the Donders Centre for Cognition (DCC), embedded in the Donders Institute for Brain, Cognition and Behaviour, and the School of Artificial Intelligence at Radboud University Nijmegen are looking for a researcher in reinforcement learning with an emphasis on safety and robustness, an interest in natural computing as well as in applications in neurotechnology and other domains such as robotics, healthcare and/or sustainability. You will be expected to perform top-quality research in (deep) reinforcement learning, actively contribute to the DBI2 consortium, interact and collaborate with other researchers and specialists in academia and/or industry, and be an inspiring member of our staff with excellent communication skills. You are also expected to engage with students through teaching and master projects not exceeding 20% of your time. Profile: * You have a PhD degree in Artificial Intelligence, Computer Science or a related discipline; * You have experience in a number of the following topics: (deep, Bayesian, safe) RL, control theory and model predictive control, applications of RL in e.g. healthcare, robotics, neurotechnology, sustainability and/or edge solutions for control of complex systems. * You have an excellent track record in scientific research, as evidenced by publications in top-tier conferences and journals. * You have a proven ability to provide inspiring teaching in English. * You are enthusiastic and you are able to work together in a team as part of the DBI2 consortium. Application deadline: April 7th To apply, please follow this link: https://www.ru.nl/en/working-at/job-opportunities/researcher-in-reinforceme…

1 0

March 22, 15:00: Machine Learning Theory Seminar++ Meeting with Hanyuan Hang
by Wouter Koolen-Wijkstra 10 Mar '23

10 Mar '23

Dear researchers, Centrum Wiskunde & Informatica (CWI) kindly invites you to the second Seminar++ meeting on Machine Learning Theory, taking place on Wednesday March 22 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 22 March will be hosted by: Hanyuang Hang <https://people.utwente.nl/h.hang> (Assistant professor at the University of Twente <https://www.utwente.nl/en/>) Bagged k-Distance for Mode-Based Clustering Using the Probability of Localized Level Sets *Abstract:* We propose an ensemble learning algorithm named bagged /k/-distance for mode-based clustering (BDMBC) by putting forward a new measurement called the probability of localized level sets (PLLS), which enables us to find all clusters for varying densities with a global threshold. On the theoretical side, we show that with a properly chosen number of nearest neighbors /k_D / in the bagged /k/-distance, the sub-sample size /s/, the bagging rounds /B/, and the number of nearest neighbors /k_L / for the localized level sets, BDMBC can achieve optimal convergence rates for mode estimation. It turns out that with a relatively small /B/, the sub-sample size /s/ can be much smaller than the number of training data /n/ at each bagging round, and the number of nearest neighbors /k_D / can be reduced simultaneously. Moreover, we establish optimal convergence results for the level set estimation of the PLLS in terms of Hausdorff distance, which reveals that BDMBC can find localized level sets for varying densities and thus enjoys local adaptivity. On the practical side, we conduct numerical experiments to empirically verify the effectiveness of BDMBC for mode estimation and level set estimation, which demonstrates the promising accuracy and efficiency of our proposed algorithm. 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/~wmkoolen/MLT_Sem23/index.html>, which runs in Spring 2023. Best regards on behalf of CWI from the program committee, Wouter Koolen

1 0

Fwd: AIM news - Game AI workshop & NMC
by Tim van Erven 09 Mar '23

09 Mar '23

Dear all, At the end of this month there will be an interesting *workshop on **Game theory for AI *organized by the Maastricht Centre Mathematics (MCM) together with the *AI and Mathematics (AIM)***initiative. See below for details. Best regards, Tim -------- Forwarded Message -------- Subject: AIM news - Game AI workshop & NMC Date: Mon, 27 Feb 2023 15:38:23 +0000 From: AI and Mathematics <aim(a)NWO.NL> To: AI and Mathematics <aim(a)NWO.NL> *News* ·*Workshop “Game theory for AI - Mathematical foundations, Algorithms and Future Challenge” @ Maastricht*** The Maastricht Centre Mathematics MCM & *AIM* are organizing a workshop on "Game theory for AI - Mathematical foundations, Algorithms and Future Challenge. The aim of this workshop is to create a new research agenda involving the Dutch AI community along a selected list of important topics. The research discussions will be guided and supported by the input of leading experts in the field. Beside networking opportunities, we aim for developing new research collaborations, connecting researchers with different expertises. Scientists at all levels of their career are invited to participate, but registrations will only be accepted on a first-come-first-serve basis. The four work packages are described below, as well as further information about location, registration and accommodation. We are looking forward to welcome you all in Maastricht! /Work//Package Leader/ Online learning in complex environments Tim van Erven (UvA) Game AI & Search Wouter Koolen (CWI) Robust AI via optimal transport & mean field games Christoph Brune (U Twente) Fast methods for large-scale bi-level programming Tristan van Leeuwen (CWI) /Venue and Dates:/ * /_Date_/: March 30 and 31, 2023. Lunches and coffee breaks will be provided. * /_Location_/: Department of Advanced Computing Sciences (DACS), Faculty of Sciences and Engineering, Maastricht University, Paul-Henri Spaaklaan 1, 6229 EN, Maastricht. * /_Registration_/: Registration via the AIM website. <https://eur05.safelinks.protection.outlook.com/?url=https%3A%2F%2Faimath.nl…>__We might be able to reimburse a limited number of participants for their accommodation. If support is needed, please mention this in the open text box in the registration * /_Contact:_/Mathias Staudigl (UM), Barbara Franci (UM) ·*Dutch Mathematics Congres (NMC) on 11 & 12 April @Utrecht*** The Dutch Mathematics Congres (NMC) brings together mathematicians from all disciplines to exchange ideas, learn from each other & network. The NMC has 4 inspiring keynote speakers, parallel sessions, award ceremonies, speed dates and workshops. In a plenary session organized by *AIM, *Johannes Schmidt-Hieber will give a presentation about statistical learning in biological neural networks. NMC takes place on 11 & 12 April 2023 at Van der Valk Hotel Utrecht. Check out the website and the flyer attached and register for NMC! <https://mathematischcongres.nl/>

1 0

March 8, 15:00: Machine Learning Theory Seminar++ Meeting with Julia Olkhovskaya
by Wouter Koolen-Wijkstra 03 Mar '23

03 Mar '23

Dear researchers, Centrum Wiskunde & Informatica (CWI) kindly invites you to the first Seminar++ meeting on Machine Learning Theory, taking place on Wednesday March 8 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 and tea will be provided in the half-time break. The meeting of 8 March will be: Julia Olkhovskaya (Department of Mathematics of the Vrije Universiteit Amsterdam) Online reinforcement learning with linear function approximation: role of the choice of policy optimization algorithm and learner’s feedback *Abstract:* We consider learning in an adversarial MDP, where the loss function can change arbitrarily between episodes, and we assume that the Q-function of any policy is linear in some known features. We discuss two recent works, providing new insights into the solution to this problem ([1], [2]). We will look at the combination of methods proposed in these two papers to achieve better theoretical guarantees on the performance of the algorithms. More precisely, we will check if taking the best from both papers can lead to an improvement: exploration bonuses from [1] and the choice of the regularizer from [2]. If there will be time, we also discuss the variation of this problem when the information available to the learner is only the cumulative loss of the learner accumulated over the episode. * [1] https://arxiv.org/pdf/2301.13087.pdf * [2] https://arxiv.org/pdf/2301.12942.pdf 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/~wmkoolen/MLT_Sem23/index.html>, which runs in Spring 2023. Best regards on behalf of CWI from the program committee, Wouter Koolen

1 0

Two PhD vacancies in Reinforcement Learning for Sustainable Energy
by Moerland, T.M. (Thomas) 20 Feb '23

20 Feb '23

Dear all, The Leiden Institute of Advanced Computer Science (LIACS) is looking for two PhD candidates in the field of Reinforcement Learning, with an emphasis on sustainable energy. Should you know an interested/suitable candidate, then further information is available at: https://www.universiteitleiden.nl/vacatures/2023/kwartaal-1/23-0952-phd-can… Best regards, Thomas Moerland

1 0

2024

2023

2022

2021

2020

Machine-learning-nederland