23 citations · 149 across the 39 of their papers we have counts for
17 papers · 1 filter
Pack only the essentials: Adaptive dictionary learning for kernel ridge regression
Daniele Calandriello, Alessandro Lazaric, Michal Valko
One of the major limits of kernel ridge regression (KRR) is that storing and manipulating the kernel matrix K_n for n samples requires O(n^2) space, which rapidly becomes unfeasibl…
Proximal Point Nash Learning from Human Feedback
Daniil Tiapkin, Daniele Calandriello, Denis Belomestny +5
Traditional Reinforcement Learning from Human Feedback (RLHF) often relies on reward models, frequently assuming preference structures like the Bradley--Terry model, which may not…
Nash Learning from Human Feedback
Rémi Munos, Michal Valko, Daniele Calandriello +14
Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Typically, RLHF involves the in…
Model-free Posterior Sampling via Learning Rate Randomization
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +6
In this paper, we introduce Randomized Q-learning (RandQL), a novel randomized model-free algorithm for regret minimization in episodic Markov Decision Processes (MDPs). To the bes…
Demonstration-Regularized RL
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +5
Incorporating expert demonstrations has empirically helped to improve the sample efficiency of reinforcement learning (RL). This paper quantifies theoretically to what extent this…
Fast Rates for Maximum Entropy Exploration
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +7
We address the challenge of exploration in reinforcement learning (RL) when the agent operates in an unknown environment with sparse or no rewards. In this work, we study the maxim…
Optimistic Posterior Sampling for Reinforcement Learning with Few Samples and Tight Guarantees
Daniil Tiapkin, Denis Belomestny, Daniele Calandriello +6
We consider reinforcement learning in an environment modeled by an episodic, finite, stage-dependent Markov decision process of horizon with states, and actions. The pe…
Scaling Gaussian Process Optimization by Evaluating a Few Unique Candidates Multiple Times
Daniele Calandriello, Luigi Carratino, Alessandro Lazaric +2
Computing a Gaussian process (GP) posterior has a computational cost cubical in the number of historical points. A reformulation of the same GP posterior highlights that this compl…
ParK: Sound and Efficient Kernel Ridge Regression by Feature Space Partitions
Luigi Carratino, Stefano Vigogna, Daniele Calandriello +1
We introduce ParK, a new large-scale solver for kernel ridge regression. Our approach combines partitioning with random projections and iterative optimization to reduce space and t…
Near-linear Time Gaussian Process Optimization with Adaptive Batching and Resparsification
Daniele Calandriello, Luigi Carratino, Alessandro Lazaric +2
Gaussian processes (GP) are one of the most successful frameworks to model uncertainty. However, GP optimization (e.g., GP-UCB) suffers from major scalability issues. Experimental…
Statistical and Computational Trade-Offs in Kernel K-Means
Daniele Calandriello, Lorenzo Rosasco
We investigate the efficiency of k-means in terms of both statistical and computational requirements. More precisely, we study a Nyström approach to kernel k-means. We analyze the…
Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
Daniele Calandriello, Luigi Carratino, Alessandro Lazaric +2
Gaussian processes (GP) are a well studied Bayesian approach for the optimization of black-box functions. Despite their effectiveness in simple problems, GP-based algorithms hardly…
On Fast Leverage Score Sampling and Optimal Learning
Alessandro Rudi, Daniele Calandriello, Luigi Carratino +1
Leverage score sampling provides an appealing way to perform approximate computations for large matrices. Indeed, it allows to derive faithful approximations with a complexity adap…
Distributed Adaptive Sampling for Kernel Matrix Approximation
Daniele Calandriello, Alessandro Lazaric, Michal Valko
Most kernel-based methods, such as kernel or Gaussian process regression, kernel PCA, ICA, or -means clustering, do not scale to large datasets, because constructing and storing…
Second-Order Kernel Online Convex Optimization with Adaptive Sketching
Daniele Calandriello, Alessandro Lazaric, Michal Valko
Kernel online convex optimization (KOCO) is a framework combining the expressiveness of non-parametric kernel models with the regret guarantees of online learning. First-order KOCO…
Analysis of Kelner and Levin graph sparsification algorithm for a streaming setting
Daniele Calandriello, Alessandro Lazaric, Michal Valko
We derive a new proof to show that the incremental resparsification algorithm proposed by Kelner and Levin (2013) produces a spectral sparsifier in high probability. We rigorously…
Incremental Spectral Sparsification for Large-Scale Graph-Based Semi-Supervised Learning
Daniele Calandriello, Alessandro Lazaric, Michal Valko +1
While the harmonic function solution performs well in many semi-supervised learning (SSL) tasks, it is known to scale poorly with the number of samples. Recent successful and scala…