2024

• Graphs in ML minicourse - Graph Laplacians workshop, November 4-8th, 2024, Eindhoven, Netherlands (EURANDOM 2024)
• Algorithmic LLM alignment (keynote) - International Conference on Machine Learning, Optimization, and Data Science, September 22 – 25, 2024, Castiglione della Pescaia, Tuscany (LOD 2024)
• Gamification of Large Language Models (keynote) - Conference on Learning Theory, June 30–July 3, 2024, Edmonton, Canada (COLT 2024)
• Nash learning from human feedback - Ghost Day, April 04-06, 2024, Poznań, Poland (GHOST 2024)
• Algorithmic LLM alignment - Princeton Language + Intelligence, February 1st, 2024, Princeton, USA (Princeton 2024)

2023

• Curious world models - European Workshop on Reinforcement Learning, September 14-16, 2023, Brussels, Belgium (EWRL 2023)
• Learning by bootstrapping: Reinforcement Learning - International #DataFestival in Yerevan, September 2-3, 2023, Yerevan, Armenia (DataFest 2023)
• Deep reinforcement learning - Advanced Course on Data Science & Machine Learning, June 10-14, 2023, Tuscany, Italy (ACDL 2023)
• World Models: Curiosity driven exploration (two master classes) - AI in Africa, January 26-27, 2023, Marrakesh, Morocco (Tech'Innov 2023)

2022

• Learning by bootstrapping - Vedatour, October 11, 2022, Bratislava, Slovakia (ESET 2022)
• Learning by bootstrapping (keynote) - Runtime Verification, September 28-30, 2022, Tbilisi, Georgia (RV 2022)
• Model-free learning for two-player zero-sum partially observable Markov games with perfect recall - ELLIS unit Milan workshop, September 8-9th, 2022, Milan, Italy (Milan 2022)
• Best of both worlds for best-arm identification - Simons program on Data-driven decision processes, September 12-16, 2022, Berkeley, California, USA (Berkeley 2022)
• Reinforcement learning (lecture) and BYOL-Explore (talk) - Eastern European Machine Learning Summer School, July, 6-14 2022, Vilnius Lithuania ( EEML 2022)

2021

• Bootstrap your own latent, Presented on Sep 11th, 2021 at DataFest Yerevan (DataFest 2021)
• Bootstrapped representation learning on graphs, Presented on June, 23 2021 at Science Academy of Turkey Machine Learning Summer School (BAYÖYO 2021) talk
• Graphs in Machine Learning, Invited guest lecture at Medical University Graz, Austria, June 2021 (HCAI 2021)
• Bootstrap Your Own Latent: A new approach to self-supervised learning, Presented on January, 2021 at MIST conference in Rajecká Lesná (MIST 2021)

2020

• Bootstrap Your Own Latent: A new approach to self-supervised learning - Google - December 10, 2020 - (Google 2020)
• Bootstrap Your Own Latent: A new approach to self-supervised learning - Reinforcement Learning seminar at Polish Academy of Sciences, November 30, 2020 - Warsaw, Poland (PAS 2020)
• BYOL works even without batch statistics - Deep learning seminar at UPJS, November 27, 2020 - Kosice, Slovakia (UPJS 2020)
• Reinforcement learning (minicourse) - Math of Machine Learning 2020 Winter School, February 19-22th, 2020 - Sochi, Russia (MML 2020)

2019

• Graphs are the new gold: The power of graphs in speeding up online learning and decision making - October 16-18, 2019 - Global Innovation Forum, Yerevan, FAST, Armenia (GIF 2019)
• Gaussian process optimization with adaptive sketching: Scalable and no regret - September 26-27, 2019 - Recent developments in kernel methods, UCL, London, UK (Gatsby 2019)
• Rotting bandits are not harder than stochastic ones - September 25-26, 2019 - Lancaster and Deepmind Bandit Workshop, London, UK (LanDeep 2019) talk
• Graphs are the new gold: The power of graphs in speeding up online learning and decision making, July 23th, 2019, Cisco in Kraków, Poland, (Cisco 2019)
• How the negative dependence broke the squadratic barrier for learning with graphs and kernels - July 5th, 2019, Yandex HQ, Moscow, Russia (Yandex 2019) talk
• Active multiple matrix completion with adaptive confidence sets - July 3-8, 2019 - RAAI Summer School 2019, Moscow Institute of Physics and Technology (RAAI 2019) talk
• How the negative dependence broke quadratic barrier for learning with graphs and kernels. - June 14-15th, 2019, ICML workshop on negative dependence, Long Beach, USA (ICML 2019) talk video
• Active block-matrix completion with adaptive confidence sets- May 28th, 2019 - Theoretical Computer Science seminar, Comenius University in Bratislava, Slovakia (CU 2019) talk
• 10 year road to breaking the quadratic barrier for graphs and matrices - February 22, 2019 - Theoretical Computer Science seminar Comenius University in Bratislava, Slovakia (CU 2019) talk
• Graphs are the new gold - February 20, 2019 - Data Analytics Meetings, P.J. Šafárik University in Košice, Slovakia (UPJS 2019)
• The power of graphs in speeding up online learning and decision making - January 25rd, 2019 - Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, UK (Cambridge 2019)
• A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption - January 7th, 2019 - Verimag, CNRS Grenoble, France (CNRS 2019) talk
• The power of graphs in speeding up online learning and decision making - January 8th, 2019 - Verimag, CNRS Grenoble, France (CNRS 2019) talk

2018

• The power of graphs in speeding up online learning and decision making - October 23rd, 2018 - DeepMind, London, UK (DeepMind 2018) talk
• Active block-matrix completion with adaptive confidence sets - Presented on September 10-13th, 2018, International Workshop Optimization and Machine Learning, CIMI, Toulouse (CIMI 2018) talk
• Online influence maximization - Presented on May 14th, 2018, Workshop on Graph Learning, LINCS, Paris (LINCS 2018)
• Recommender systems - Presented on March 22nd, 2018, Journée Big data, Polytech'Lille (Polytech'Lille 2018)
• Pliable rejection sampling - Presented on February 8th, 2018 at GDR Isis, Télécom ParisTech in Paris (ISIS 2018) talk
• Graph Bandits - Presented on January 7th, 2018 at MIST conference in Rajecká Lesná (MIST 2018)

2017

• SequeL, graphs in ML, and online recommender systems - November 9th, 2017 at R&DV du Plateau Inria 2017 in Lille, France (Euratechnologies 2017) talk
• Sequential sampling for kernel matrix approximation and online learning - September 19th, 2017 - DeepMind, London, UK (DeepMind 2017)
• Active learning on networks and online influence maximization - September 18th, 2017 - Decision Theory and Network Science: Methods and Applications, Lancaster, UK (STOR-i 2017) talk
• Side observation in graph bandits - August 11th, 2017 - ICML 2017 workshop on Picky Learners , Sydney, Australia (ICML 2017)
• (Impromptu talk) Efficient second-order online kernel learning with adaptive embedding - July 9th, 2017 - Conference on Learning Theory, Amsterdam, Netherlands (COLT 2017) talk
• Distributed sequential sampling for kernel matrix approximation - Presented on June 29nd, 2017 at L’Institut de Mathématiques de Toulouse, France (IMT 2017) talk
• Online sequential solutions for recommender systems Invited talk on June 14th, 2017 at Journées Scientifiques Inria 2017 in Nice, France (JS 2017)
• Mais où se cache Justin Bieber ? Ou comment maximiser la détection des influenceurs sur les réseaux sociaux ? Popularization invited talk on May 30th, 2017 at Inria Lille, France (13:45 2017)
• Invited talk on March 30th, 2017 at Dating day 2017 in Lille, France (Dating 2017)
• Distributed sequential sampling for kernel matrix approximation - Presented on March 22nd, 2017 at Joint seminar of MuSyAD group of Universität Potsdam and Amazon at Amazon Berlin, Germany (Berlin 2017) talk

2016

• Graphs in online machine learning - Presented on December 21nd, 2016 at Textkernel talks in Amsterdam, Netherlands (TK 2016)
• Where is Justin Bieber? - Presented on September 22nd, 2016 at Seminar of Theoretical Computer Science Comenius University in Bratislava, Slovakia (CU 2016) talk
• Bandit learning - Presented on September 15-19th, 2016 at Information technologies - Applications and Theory 2016 in Tatranské Matliare, High Tatras, Slovakia (ITAT 2016)
• Decision-making on graphs without graphs - Presented on June 16, 2016 at Graph-based Learning and Graph Mining 2016 in Lille (GBLGM 2016)
• Sequential learning on graphs with limited feedback - Presented on May 11-13th, 2016 at Data Driven Approach to Networks and Language 2016 at ENS Lyon, France (NETSpringLyon 2016) talk
• Benefits of Graphs in Bandit Settings - Presented on January 11-12th, 2016 at Multi-armed Bandit Workshop 2016 at STOR-i, Lancaster University, UK (STOR-i 2016) talk

2015 and before

• Online decision-making on graphs - Presented on April 14th, 2015 at DaSciM, LIX, École Polytechnique, France (X 2015)
• Bandits on Graphs: Exploiting Smoothness and Side Observations, Presented on December 16th, 2014 at CMLA at ENS Cachan, France (ENS 2014) talk
• Optimistic Optimization - Presented on January 7th, 2014 at MIST conference in Fačkovské sedlo (MIST 2014)
• Sequential Face Recognition with Minimal Feedback - Presented on May 2nd, 2013 at 30 minutes of Science, Lille (30MIN 2013)
• One Class Learning From Streams of Unlabeled Data - Presented on September 17th, 2012 at Large-scale Online Learning and Decision Making (LSOLDM 2012)
• Scaling Graph-Based Algorithms - Presented on July 20th, 2012 at LAMPADA workshop (LAMPADA 2012)
• Large Scale Sequential Learning - Presented on April 8th, 2012 at Slovak Oxford Science (Oxford UK 2012)
• Adaptive Graph-Based Algorithms - Presented on July 6th, 2011 at Microsoft Research Redmond (MSR 2011) video video archive
• Online Semi-Supervised Learning- Presented in July 2011, at MPI Tuebingen, Germany (MPI 2011)
• Semi-supervised Learning with Random Walks on Graphs - Presented at 6th Comenius University Alumni conference (TAM 2009) talk