Site map
An overview of the available content on this site. Keep the pointer still over an item for a few seconds to get its description.
-
Events
- Machine Learning Reading Group goes live
- Wouter Koolen | On the Complexity of Best Arm Identification in Multi-Armed Bandit Models ---- Kaufmann, Cappé and Garivier
- Tom Sterkenburg | Prequential randomness and probability ---- Vovk and Shen
- Nishant Mehta | Learnability, Stability and Uniform Convergence
- Cristóbal Guzmán | Efficient Noise-Tolerant Learning from Statistical Queries ---- Michael Kearns
- Haipeng Luo | Efficient Second Order Online Learning via Sketching
- Haipeng Luo | Variance-Reduced and Projection-Free Stochastic Optimization
- Hannu Reittu | A graph compression method inspired by Szemerédi's Regularity Lemma
- Wouter Koolen | BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits ---- Rakhlin and Sridharan
- Steve Homer | Automatically Scalable Computation
- Rianne de Heide | Bayesian regression with sparse priors
- Wouter Koolen | MetaGrad: Online Convex Optimization in Individual-Sequence and Stochastic Settings
- Nishant Mehta | Sample compression schemes for VC classes
- Gleb Polevoy | The Game of Reciprocation Habits
- James Ridgway | On the properties of variational approximations of Gibbs posteriors
- Emilie Kaufmann | Revisiting the Exploration/Exploitation trade-off in bandit models
- Wouter M. Koolen | MetaGrad: Multiple Learning Rates in Online Learning
- National NIPS Debriefing
- Wouter Koolen | Harder, Better, Faster, Stronger Convergence Rates for Least-Squares Regression ---- Dieuleveut, Flammarion, Bach
- Rianne de Heide | Sequential nonparametric testing with the law of the iterated logarithm - Balsubramani, Ramdas
- Peter Grunwald | "Bousquet's Version of Talagrand's Inequality": What it is, How to Prove It, and Why It Matters
- Jonas Teuwen | Predicting survival in lung cancer with neural networks
- Sjoerd Dirksen | Dimensionality reduction with Johnson-Lindenstrauss embeddings
- Vivek Farias | Learning Preferences with Side Information
- Rianne de Heide | Sequential nonparametric testing with the law of the iterated logarithm - Balsubramani, Ramdas
- Judith ter Schure | Brownian Motion in Sequential Analysis
- Yuri Gurevich | Impugning Alleged Randomness
- Alexander Ly | “Jeffreys’s” Bayes factors
- Marc Volkert | Confidence Bound Algorithms in Game Trees
- Generalized/safe Bayes, NML and learning theory ---- Peter Grünwald
- The paradox of German high-level cryptography in WWII ---- Sandy Zabell
- The Matrix-F Prior for Estimating and Testing Covariance Matrices ---- Joris Mulder
- Algorithms for Climate Informatics: Learning from spatiotemporal data with both spatial and temporal non-stationarity ---- Claire Monteleoni
- Adaptive signal denoising with provable guarantees via first-order algorithms ---- Dmitrii Ostrovskii
- Past and Future Dependencies in Meta-Analysis: Flexible Statistics for Reducing Health Research Waste -- Judith ter Schure
- Function estimation on a large graph using Bayesian Laplacian regularization ---- Alice Kirichenko
- On consistency of spectral graph algorithms for community detection in networks ---- Ambedkar Dukkipati
- Double meeting on Mixing and Mixability ---- Dirk van der Hoeven and Zakaria Mhammedi
- Compressibility and Generalization in Large-Scale Deep Learning ---- Victor Veitch
- Data Science at Netflix ---- Tristan Cossio
- Monte Carlo Tree Search for Asymmetric Trees ---- Thomas Moerland
- Optimal Clustering Algorithms in Block Markov Chains ---- Jaron Sanders
- Fast Rate Conditions in Statistical Learning (MSc Practice talk) ---- Muriel Perez
- Game-Theoretic Statistics ---- Glenn Shafer
- Moment based data analysis ---- Edouard Pauwels
- PAC Bounds for Multi-Armed Bandit and Markov Decision Processes ---- Wouter Koolen
- Bayesian Reinforcement Learning for Problems with State Uncertainty ---- Frans Oliehoek
- Lower bounds for pure exploration ---- Rémy Degenne
- Spending functions ---- Judith ter Schure
- Thompson Sampling for Pure Exploration ---- Rianne de Heide
- Causal Bandits ---- Thijs van Ommen
- Testing with online FDR control ---- Rianne de Heide
- Hyperband: A novel bandit-based approach to hyperparameter optimization ---- Rianne de Heide
- Machine learning of equivariant functions inspired by atomistic modelling ---- Bas Braams, CWI
- The truth-convergence of open-minded Bayesianism ---- Rianne de Heide
- A small tour of time-uniform concentration inequalities and some open problems ---- Odalric Ambryn-Maillard
- DPPs everywhere: repulsive point processes for Monte Carlo integration, signal processing and machine learning ---- Rémi Bardenet
- Efficient exploration in sequential decision making problems ---- Yasin Abbasi
- Testing Conditional Independence on Discrete Data using Stochastic Complexity ---- Alexander Marx
- Some bias/optional stopping puzzles for the optional stopping p-hacker --- Judith ter Schure
- Sub-Gaussians in game-theoretic probability --- Wouter Koolen
- New Convergence Aspects of Stochastic Gradient Descend with Diminishing Learning Rate ---- Marten van Dijk
- Regret analysis of the Piyavskii-Shubert algorithm ---- Sébastien Gerchinovitz
- Fixed confidence guarantees for Bayesian best-arm identification --- Rianne de Heide
- Towards safe tests for correlations and partial correlations --- Alexander Ly
- The GROW S-value, the Bayes factor minimizing KL divergence and the Haar prior --- Peter Grünwald
- Minimizing Regret in Multi-armed Bandit Models by Iterative Saddle-point Solving ---- Wouter Koolen
- The GROW S-value, The Haar prior, The KL minimizer, and Lai's proof --- Peter Grünwald
- Survival Analysis --- Sanne Willems
- Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits ---- Julia Olkhovskaya
- ML Seminar --- Muriel Perez --- Haar measures
- ML Seminar --- Muriel: Haar Priors part 2
- Private Hypothesis Testing via Robustness ---- Audra McMillan
- ML Seminar --- Peter Grünwald --- PAC-Bayesian Un-Expected Bernstein Inequality
- ML Seminar --- Rosanne Turner --- Why point priors in GROW S-values for 2x2 contingency tables
- ML Seminar --- Sanne Willems --- Survival Analysis
- ML Seminar --- Judith ter Schure --- discussion about null hypothesis testing v.s. BAI
- ML Seminar --- Rianne de Heide --- Submodular optimization
- ML Seminar --- Muriel Perez --- Haar measures
- ML Seminar --- Wouter Koolen --- Confidence intervals
- ML Seminar: Safe interim meta-analysis --- Judith ter Schure
- ML Seminar - Muriel Perez - Amenability
- ML Seminar - Muriel Perez - Amenability Part II
- ML Seminar - Judith ter Schure - Enough Bayesian or less selection please?! The stopping rule principle, accumulation bias and publication bias
- A spotlight on statistical model assumptions ---- Christian Hennig
- An asymptotically optimal algorithm for the maximin action identification problem --- Guanyu Jin
- A class of ie-merging functions ---- Muriel Perez
- Sanne Willems - Variability in the interpretation of probability phrases used in Dutch news articles - a risk for miscommunication
- Improving (ε,δ)-Monte Carlo tree search using spherical confidence regions --- Thomas Schiet
- Valid sequential inference on probability forecast performance
- Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote ---- Yi Shan Wu
- Brainstorm session with Susan Murphy (CANCELLED)
- Recent advances in E-values ---- Alexander Henzi
- Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables ---- Yi-Shan Wu
- Universal densities for stationary measures ---- Łukasz Dębowski
- Could we lose control of AI? Exploring the arguments of an old and reignited debate. ---- Reuben Adams
-
Papers
- Learning with Square Loss: Localization through Offset Rademacher Complexity ---- Tengyuan Liang, Alexander Rakhlin and Karthik Sridharan
- A Chaining Algorithm for Online Nonparametric Regression ---- Pierre Gaillard and Sébastien Gerchinovitz
- Exp-Concavity of Proper Composite Losses ---- Parameswaran Kamalaruban, Robert Williamson and Xinhua Zhang
- Competitive Distribution Estimation: Why is Good-Turing Good ---- Alon Orlitsky and Ananda Theertha Suresh
- On Elicitation Complexity ---- Rafael Frongillo and Ian Kash
- Sparse Adaptive Dirichlet-Multinomial-like Processes ---- Marcus Hutter
- No more pesky learning rates ---- Tom Schaul, Sixin Zhang, Yann LeCun
- Regret Minimization in Games with Incomplete Information ---- M. Zinkevich, M. Bowling, M. Johanson, C. Piccione.
- Coin Betting and Parameter-Free Online Learning ---- Francesco Orabona, Dávid Pál