23 citations · 149 across the 39 of their papers we have counts for
39 papers
DiffusionGemma Technical Report
DiffusionGemma Team, Adrien Ali Taïga, James Assiene +41
We introduce DiffusionGemma, an experimental open-weight language model that uses discrete diffusion to generate text at exceptionally high speed. Rather than decoding one token at…
Large-scale semi-supervised learning with online spectral graph sparsification
Daniele Calandriello, Alessandro Lazaric, Michal Valko
We introduce Sparse-HFS, a scalable algorithm that can compute solutions to SSL problems using only O(n polylog(n)) space and O(m polylog(n)) time.
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…
Improved large-scale graph learning through ridge spectral sparsification
Daniele Calandriello, Ioannis Koutis, Alessandro Lazaric +1
Graph-based techniques and spectral graph theory have enriched the field of machine learning with a variety of critical advances. A central object in the analysis is the graph Lapl…
Analysis of Nystrom method with sequential ridge leverage scores
Daniele Calandriello, Alessandro Lazaric, Michal Valko
Large-scale kernel ridge regression (KRR) is limited by the need to store a large kernel matrix K_t. To avoid storing the entire matrix K_t, Nystrom methods subsample a subset of c…
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…
On Teacher Hacking in Language Model Distillation
Daniil Tiapkin, Daniele Calandriello, Johan Ferret +4
Post-training of language models (LMs) increasingly relies on the following two stages: (i) knowledge distillation, where the LM is trained to imitate a larger teacher LM, and (ii)…
Building Math Agents with Multi-Turn Iterative Preference Learning
Wei Xiong, Chengshuai Shi, Jiaming Shen +10
Recent studies have shown that large language models' (LLMs) mathematical problem-solving capabilities can be enhanced by integrating external tools, such as code interpreters, and…
Offline Regularised Reinforcement Learning for Large Language Models Alignment
Pierre Harvey Richemond, Yunhao Tang, Daniel Guo +15
The dominant framework for alignment of large language models (LLM), whether through reinforcement learning from human feedback or direct preference optimisation, is to learn from…
Understanding the performance gap between online and offline alignment algorithms
Yunhao Tang, Daniel Zhaohan Guo, Zeyu Zheng +8
Reinforcement learning from human feedback (RLHF) is the canonical framework for large language model alignment. However, rising popularity in offline alignment algorithms challeng…
Multi-turn Reinforcement Learning from Preference Human Feedback
Lior Shani, Aviv Rosenberg, Asaf Cassel +10
Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate re…
Human Alignment of Large Language Models through Online Preference Optimisation
Daniele Calandriello, Daniel Guo, Remi Munos +10
Ensuring alignment of language models' outputs with human preferences is critical to guarantee a useful, safe, and pleasant user experience. Thus, human alignment has been extensiv…
Generalized Preference Optimization: A Unified Approach to Offline Alignment
Yunhao Tang, Zhaohan Daniel Guo, Zeyu Zheng +7
Offline preference optimization allows fine-tuning large models directly from offline data, and has proved effective in recent alignment practices. We propose generalized preferenc…
Decoding-time Realignment of Language Models
Tianlin Liu, Shangmin Guo, Leonardo Bianco +7
Aligning language models with human preferences is crucial for reducing errors and biases in these models. Alignment techniques, such as reinforcement learning from human feedback…
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…
A General Theoretical Paradigm to Understand Learning from Human Preferences
Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot +4
The prevalent deployment of learning from human preferences through reinforcement learning (RLHF) relies on two important approximations: the first assumes that pairwise preference…
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…
Unlocking the Power of Representations in Long-term Novelty-based Exploration
Alaa Saade, Steven Kapturowski, Daniele Calandriello +6
We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for…
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…
Understanding Self-Predictive Learning for Reinforcement Learning
Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond +13
We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their…
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…
BYOL-Explore: Exploration by Bootstrapped Prediction
Zhaohan Daniel Guo, Shantanu Thakoor, Miruna Pîslar +11
We present BYOL-Explore, a conceptually simple yet general approach for curiosity-driven exploration in visually-complex environments. BYOL-Explore learns a world representation, t…
Information-theoretic Online Memory Selection for Continual Learning
Shengyang Sun, Daniele Calandriello, Huiyi Hu +2
A challenging problem in task-free continual learning is the online selection of a representative replay memory from data streams. In this work, we investigate the online memory se…