- Machine-learning-nederland

Thematic seminar: Tor Lattimore, Friday April 22, 16h00
by Tim van Erven 11 Apr '22

11 Apr '22

Dear all, On Friday April 22 we have Tor Lattimore from DeepMind speaking in the thematic seminar. *Tor Lattimore *(DeepMind, http://tor-lattimore.com) *Friday April 22*, 16h00-17h00 Online on Zoom: *https://uva-live.zoom.us/j/88233925917* Meeting ID: 882 3392 5917 *Minimax Regret for Partial Monitoring: Infinite Outcomes and Rustichini's Regret * The information ratio developed by Russo and Van Roy (2014) is a powerful tool that was recently used to derive upper bounds on the regret for challenging sequential decision-making problems. I will talk about how a generalised version of this machinery can be used to derive lower bounds and give an application showing that a version of mirror descent is minimax optimal for partial monitoring using Rustichini's definition of regret. Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ *Upcoming talks: *Jun. 10,***Julia Olkhovskaya <https://sites.google.com/view/julia-olkhovskaya/home>*, Vrije Universiteit -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

Reminder Thematic seminar: Nicolo Cesa-Bianchi, Fri April 8, 11h00
by Tim van Erven 07 Apr '22

07 Apr '22

Dear all, This Friday we have Nicolò Cesa-Bianchi from Università degli Studi di Milano in the thematic seminar. Note the unusual time, at *11h00* in the morning! *Nicolò Cesa-Bianchi *(Università degli Studi di Milano, https://cesa-bianchi.di.unimi.it/) *Friday April 8*, 11h00-12h00 Online on Zoom: https://uva-live.zoom.us/j/83684658173 Meeting ID: 836 8465 8173 *The power of cooperation in networks of learning agents * We study the power of cooperation in a network of communicating agents that solve a learning task. Agents use an underlying communication network to get information about what the other agents know. In the talk, we show the extent to which cooperation allows to prove performance bounds that are strictly better than the known bounds for non-cooperating agents. Our results are formulated in the setting of sequential decision-making with partial feedback. Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ *Upcoming talks: *Apr. 22, *Tor Lattimore <https://mschauer.github.io/StructuresSeminar/#Lattimore>*, DeepMind Jun. 10,***Julia Olkhovskaya <https://sites.google.com/view/julia-olkhovskaya/home>*, Vrije Universiteit -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

Fwd: StatMathAppli 2022, August 29 till September 2, Fréjus, France : registration is open!
by Pires da Silva Castro, Rui 06 Apr '22

06 Apr '22

Dear Colleagues, The following event might be appealing our communities. All the best, Rui — Dept. of Mathematics and Computer Science, TU/e http://www.win.tue.nl/~rmcastro | +31 40 247 2499 Begin forwarded message: From: statmathappli <statmathappli(a)inrae.fr<mailto:statmathappli@inrae.fr>> Subject: StatMathAppli 2022, August 29 till September 2, Fréjus, France : registration is open! Date: 28 March 2022 at 14:07:03 CEST To: statmathappli <statmathappli(a)inrae.fr<mailto:statmathappli@inrae.fr>> Dear colleague, Please find below the annoucement for the conference StatMathAppli 2022. Thank you in advance for forwarding it to your lab. Best regards, Christophe Giraud and Estelle Kuhn, for the organizing committee ------------------------------- Dear colleague, The next edition of StatMathAppli 2022 will take place at Villa Clythia in Fréjus, France, from August 29 till September 2: statmathappli.mathnum.inrae.fr<https://eur02.safelinks.protection.outlook.com/?url=http%3A%2F%2Fstatmathap…> The conference provides to European statisticians, including PhD and young researchers, the opportunity to meet, present their work, and initiate collaborations. The program includes (selected) contributed talks, and two courses given by world-renowned researchers. For the 2022 Edition, we are delighted to welcome as guest lecturer Rebecca Willett<https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwillett.p…> (Chicago University) on "Regularization Induced by Neural Network Architectures" and Richard Nickl<https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.dpmms…> (Cambridge University) on "Bayesian non-linear statistical inverse problems". Registration is open till Friday, June 17. (https://statmathappli.mathnum.inrae.fr/fr/inscription<https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fstatmatha…>) Please note that, the number of places being limited, the application process consists in a pre-registration on the website, followed by a registration after validation of your application by email from the committee. First arrived, first served. Abstract submission will be open from Monday, April 25 till Friday, June 24. Looking forward to welcome you in Fréjus this summer! Christophe Giraud and Estelle Kuhn, for the organizing committee

1 0

Thematic seminar: Nicolo Cesa-Bianchi, Fri April 8, 11h00
by Tim van Erven 04 Apr '22

04 Apr '22

Dear all, This Friday we have Nicolò Cesa-Bianchi from Università degli Studi di Milano in the thematic seminar. Note the unusual time, at *11h00* in the morning! *Nicolò Cesa-Bianchi *(Università degli Studi di Milano, https://cesa-bianchi.di.unimi.it/) *Friday April 8*, 11h00-12h00 Online on Zoom: https://uva-live.zoom.us/j/83684658173 Meeting ID: 836 8465 8173 *The power of cooperation in networks of learning agents * We study the power of cooperation in a network of communicating agents that solve a learning task. Agents use an underlying communication network to get information about what the other agents know. In the talk, we show the extent to which cooperation allows to prove performance bounds that are strictly better than the known bounds for non-cooperating agents. Our results are formulated in the setting of sequential decision-making with partial feedback. Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ *Upcoming talks: *Apr. 22, *Tor Lattimore <https://mschauer.github.io/StructuresSeminar/#Lattimore>*, DeepMind Jun. 10,***Julia Olkhovskaya <https://sites.google.com/view/julia-olkhovskaya/home>*, Vrije Universiteit -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

NeurIPS Debriefing - Scheduling Change
by Jack Mayo 15 Mar '22

15 Mar '22

Dear all, Due to one of the speakers falling ill, we have had to reschedule some of the talks for today's NeurIPS debriefing. The new schedule is: Today, 14h00-16h30 This year’s meeting will be online, via zoom: https://uva-live.zoom.us/j/84087666831<https://eur04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuva-live.…> 14:00-14:30 Julia Olkhovskaya (VU) Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination<https://proceedings.neurips.cc/paper/2021/hash/9d684c589d67031a627ad33d59db…> by Foster, Krishnamurthy 14:30-15:00 Ahmad Hammoudeh (University of Mons, ISIA Lab & MAIA artificial intelligence Lab) On the Frequency Bias of Generative Models<https://papers.nips.cc/paper/2021/hash/96bf57c6ff19504ff145e2a32991ea96-Abs…> by Schwarz, Liao, Geiger 15:00-15:15 Break 15:15-15:45 Hidde Fokkema (UvA) Framing RNN as a kernel method: A neural ODE approach<https://proceedings.neurips.cc/paper/2021/hash/18a9042b3fc5b02fe3d57fea87d6…> by Fermanian, Marion, Vert, Biau Note that we are still allowing for 30 mins extra 'overflow time' on top of the schedule. For up to date information and an overview of past meetings, see www.timvanerven.nl/neurips-debriefing/<https://eur04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.timvan…> Best regards, Jack J. Mayo<https://eur04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fjackjmayo.…> (j.j.mayo(a)uva.nl<mailto:j.j.mayo@uva.nl>) Tim van Erven<https://eur04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.timvan…> (tim(a)timvanerven.nl<mailto:tim@timvanerven.nl>)

1 0

Reminder: NeurIPS 2021 debriefing, Tue March 15, 14h00-17h00
by Tim van Erven 14 Mar '22

14 Mar '22

Dear all, This is a reminder fortomorrow's NeurIPS debriefing, wherein PhD students and/or senior researchers will briefly present the paper they found the most interesting atNeurIPS2021. The program will be entirely online, via zoom. *Tue March 15, 2022**, 14h00-17h00** ***This year’s meeting will be online, via *zoom*: https://uva-live.zoom.us/j/84087666831 14:00-14:30 Mustafa Celikok (TU Delft) Bayesian Bellman Operators <https://proceedings.neurips.cc/paper/2021/hash/7180cffd6a8e829dacfc2a31b3f7…> by Fellows, Hartikainen, Whiteson 14:30-15:00 Julia Olkhovskaya (VU) Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination <https://proceedings.neurips.cc/paper/2021/hash/9d684c589d67031a627ad33d59db…> by Foster, Krishnamurthy 15:00-15:30 Break 15:30-16:00 Ahmad Hammoudeh (University of Mons, ISIA Lab & MAIA artificial intelligence Lab) On the Frequency Bias of Generative Models <https://papers.nips.cc/paper/2021/hash/96bf57c6ff19504ff145e2a32991ea96-Abs…> by Schwarz, Liao, Geiger 16:00-16:30 Hidde Fokkema (UvA) Framing RNN as a kernel method: A neural ODE approach <https://proceedings.neurips.cc/paper/2021/hash/18a9042b3fc5b02fe3d57fea87d6…> by Fermanian, Marion, Vert, Biau Note that we are allowing for 30 mins extra 'overflow time' on top of the schedule. The format is to have 2.5 hours of short talks (in English). It is not required to have attendedNeurIPS, and presenters would usually not present their own papers. Talks are generally quite informal, and we like to keep a friendly atmosphere, so this is an ideal opportunity for PhD students to gain experience in presenting. For up to date information and an overview of past meetings, see www.timvanerven.nl/neurips-debriefing/ <https://eur04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.timvan…> Best regards, Jack J. Mayo <http://jackjmayo.nl> (j.j.mayo(a)uva.nl) Tim van Erven <http://www.timvanerven.nl/> (tim(a)timvanerven.nl) -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

Reminder: Thematic seminar: Tomer Koren, Fri March 11, 16h00
by Tim van Erven 11 Mar '22

11 Mar '22

Dear all, This Friday we have Tomer Koren from Tel Aviv University in the thematic seminar: *Tomer Koren *(Tel Aviv University, https://tomerkoren.github.io/) *Friday March 11*, 16h00-17h00 Online on Zoom: https://uva-live.zoom.us/j/85690850169 Meeting ID: 856 9085 0169 Please also join for online drinks after the talk. * Benign Underfitting of Stochastic Gradient Descent* We study to what extent may stochastic gradient descent (SGD) be understood as a ``conventional'' learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex optimization framework, where SGD is classically known to minimize the population risk at an optimal rate, and prove that, surprisingly, there exist problem instances where the SGD solution exhibits both empirical risk and generalization gap lower bounded by a universal constant. Consequently, it turns out that SGD is not algorithmically stable in any sense, and its generalization ability cannot be explained by uniform convergence or any other currently known generalization bound technique for that matter (other than that of its classical analysis). Time permitting, we will discuss related results for with-replacement SGD, multi-epoch SGD, and full-batch gradient descent. Based on joint works with Idan Amir, Roi Livni, Yishay Mansour and Uri Sherman. Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ *Upcoming talks: *Mar. 25, *Nicolò Cesa-Bianchi <https://mschauer.github.io/StructuresSeminar/#CesaBianchi>**, *Università degli Studi di Milano Apr. 22, *Tor Lattimore <https://mschauer.github.io/StructuresSeminar/#Lattimore>*, DeepMind Jun. 10,***Julia Olkhovskaya <https://sites.google.com/view/julia-olkhovskaya/home>*, Vrije Universiteit -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 1

NeurIPS 2021 debriefing, March 15, 14h00-17h00
by Tim van Erven 02 Mar '22

02 Mar '22

Dear all, We have set a date and preliminary program for this year's (online)NeurIPS debriefing, wherein PhD students and/or senior researchers will briefly present the paper they found the most interesting atNeurIPS2021. *Tue March 15, 2022**, 14h00-17h00** ***This year’s meeting will be online, via *zoom*: https://uva-live.zoom.us/j/84087666831 14:00-14:30 Mustafa Celikok (TU Delft) Bayesian Bellman Operators <https://proceedings.neurips.cc/paper/2021/hash/7180cffd6a8e829dacfc2a31b3f7…> by Fellows, Hartikainen, Whiteson 14:30-15:00 Julia Olkhovskaya (VU) Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination <https://proceedings.neurips.cc/paper/2021/hash/9d684c589d67031a627ad33d59db…> by Foster, Krishnamurthy 15:00-15:30 Break 15:30-16:00 Ahmad Hammoudeh (University of Mons, ISIA Lab & MAIA artificial intelligence Lab) On the Frequency Bias of Generative Models <https://papers.nips.cc/paper/2021/hash/96bf57c6ff19504ff145e2a32991ea96-Abs…> by Schwarz, Liao, Geiger 16:00-16:30 Hidde Fokkema (UvA) Framing RNN as a kernel method: A neural ODE approach <https://proceedings.neurips.cc/paper/2021/hash/18a9042b3fc5b02fe3d57fea87d6…> by Fermanian, Marion, Vert, Biau The format is to have 2.5 hours of short talks (in English). It is not required to have attendedNeurIPS, and presenters would usually not present their own papers. Talks are generally quite informal, and we like to keep a friendly atmosphere, so this is an ideal opportunity for PhD students to gain experience in presenting. For up to date information and an overview of past meetings, see www.timvanerven.nl/neurips-debriefing/ <https://eur04.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.timvan…> Best regards, Jack J. Mayo <http://jackjmayo.nl> (j.j.mayo(a)uva.nl) Tim van Erven <http://www.timvanerven.nl/> (tim(a)timvanerven.nl) -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

Reminder: BeNeRL registration, Friday June 3 @ Leiden University
by Moerland, T.M. (Thomas) 28 Feb '22

28 Feb '22

Dear reinforcement learning researcher, A quick reminder to register for the Belgium-Netherlands workshop on Reinforcement Learning (or, if you have already registered, forward this email to an interested colleague). We initially aimed for 75 spots, but RL interest in the region has clearly grown, corona regulations have been lifted, and we managed to book a bigger room, so you can still register through: https://rlg.liacs.nl/benerl-2022<https://rlg.liacs.nl/benerl-2022> (currently at 100 registrations). Hope to see you in June. Kind regards, Thomas Moerland & Aske Plaat

1 0

Thematic seminar: Tomer Koren, Fri March 11, 16h00
by Tim van Erven 25 Feb '22

25 Feb '22

Dear all, We will continue the thematic seminar with a series of online talks. Our next speaker is Tomer Koren from Tel Aviv University. *Tomer Koren *(Tel Aviv University, https://tomerkoren.github.io/) *Friday March 11*, 16h00-17h00 Online on Zoom: https://uva-live.zoom.us/j/85690850169 Meeting ID: 856 9085 0169 Please also join for online drinks after the talk. ** * Benign Underfitting of Stochastic Gradient Descent* We study to what extent may stochastic gradient descent (SGD) be understood as a ``conventional'' learning rule that achieves generalization performance by obtaining a good fit to training data. We consider the fundamental stochastic convex optimization framework, where SGD is classically known to minimize the population risk at an optimal rate, and prove that, surprisingly, there exist problem instances where the SGD solution exhibits both empirical risk and generalization gap lower bounded by a universal constant. Consequently, it turns out that SGD is not algorithmically stable in any sense, and its generalization ability cannot be explained by uniform convergence or any other currently known generalization bound technique for that matter (other than that of its classical analysis). Time permitting, we will discuss related results for with-replacement SGD, multi-epoch SGD, and full-batch gradient descent. Based on joint works with Idan Amir, Roi Livni, Yishay Mansour and Uri Sherman. Seminar organizers: Tim van Erven Botond Szabo https://mschauer.github.io/StructuresSeminar/ *Upcoming talks: *Mar. 25, *Nicolò Cesa-Bianchi <https://mschauer.github.io/StructuresSeminar/#CesaBianchi>**, *Università degli Studi di Milano Apr. 22, *Tor Lattimore <https://mschauer.github.io/StructuresSeminar/#Lattimore>*, DeepMind Jun. 10,***Julia Olkhovskaya <https://sites.google.com/view/julia-olkhovskaya/home>*, Vrije Universiteit ** -- Tim van Erven<tim(a)timvanerven.nl> www.timvanerven.nl

1 0

2024

2023

2022

2021

2020

Machine-learning-nederland