Publications

Leveraging Function Space Aggregation for Federated Learning at Scale
Nikita Dhawan
Nicole Elyse Mitchell
Zachary Charles
Zachary Garrett
Gintare Karolina Dziugaite
The federated learning paradigm has motivated the development of methods for aggregating multiple client updates into a global server model,… (voir plus) without sharing client data. Many federated learning algorithms, including the canonical Federated Averaging (FedAvg), take a direct (possibly weighted) average of the client parameter updates, motivated by results in distributed optimization. In this work, we adopt a function space perspective and propose a new algorithm, FedFish, that aggregates local approximations to the functions learned by clients, using an estimate based on their Fisher information. We evaluate FedFish on realistic, large-scale cross-device benchmarks. While the performance of FedAvg can suffer as client models drift further apart, we demonstrate that FedFish is more robust to longer local training. Our evaluation across several settings in image and language benchmarks shows that FedFish outperforms FedAvg as local training epochs increase. Further, FedFish results in global networks that are more amenable to efficient personalization via local fine-tuning on the same or shifted data distributions. For instance, federated pretraining on the C4 dataset, followed by few-shot personalization on Stack Overflow, results in a 7% improvement in next-token prediction by FedFish over FedAvg.
2024-02-12
TMLR (accepté)
doi.org
openreview.net
Metrics reloaded: Pitfalls and recommendations for image analysis validation
Lena Maier-Hein
Annika Reinke
Evangelia Christodoulou
Ben Glocker
PATRICK GODAU
Fabian Isensee
Jens Kleesiek
Michal Kozubek
Mauricio Reyes
MICHAEL A. RIEGLER
Manuel Wiesenfarth
Michael Baumgartner
Matthias Eisenmann
DOREEN HECKMANN-NÖTZEL
A. EMRE KAVUR
TIM RÄDSCH
Minu Dietlinde Tizabi
LAURA ACION
Michela Antonelli
Tal Arbel … (voir 47 de plus)
Spyridon Bakas
Peter Bankhead
Allison Benis
M. Jorge Cardoso
Veronika Cheplygina
BETH A. CIMINI
Gary S. Collins
Keyvan Farahani
Bram van Ginneken
Daniel A. Hashimoto
Michael M. Hoffman
Merel Huisman
Pierre Jannin
CHARLES E. KAHN
Alexandros Karargyris
Alan Karthikesalingam
H. Kenngott
Annette Kopp-Schneider
Anna Kreshuk
Tahsin Kurc
Bennett Landman
GEERT LITJENS
Amin Madani
Klaus Maier-Hein
Anne L. Martel
Peter Mattson
ERIK MEIJERING
Bjoern Menze
David Moher
KAREL G.M. MOONS
Henning Müller
Felix Nickel
Brennan Nichyporuk
Jens Petersen
NASIR RAJPOOT
Nicola Rieke
Julio Saez-Rodriguez
Clarisa S'anchez Guti'errez
SHRAVYA SHETTY
M. Smeden
Carole H. Sudre
Ronald M. Summers
Abdel Aziz Taha
Sotirios A. Tsaftaris
Ben Van Calster
Gael Varoquaux
PAUL F. JÄGER
2024-02-12
Nature Methods (publié)
doi.org
arxiv.org
Nearest Neighbour Score Estimators for Diffusion Generative Models
Matthew Niedoba
Dylan Green
Saeid Naderiparizi
Vasileios Lioutas
Jonathan Wilder Lavington
Xiaoxuan Liang
Yunpeng Liu
Ke Zhang
Setareh Dabiri
Adam Ścibior
Berend Zwartsenberg
Frank N. Wood
2024-02-12
ArXiv (prépublication)
doi.org
arxiv.org
Understanding metric-related pitfalls in image analysis validation
Annika Reinke
Minu Dietlinde Tizabi
Michael Baumgartner
Matthias Eisenmann
DOREEN HECKMANN-NÖTZEL
A. EMRE KAVUR
TIM RÄDSCH
Carole H. Sudre
LAURA ACION
Michela Antonelli
Tal Arbel
Spyridon Bakas
Allison Benis
Arriel Benis
Matthew Blaschko
FLORIAN BUETTNER
M. Jorge Cardoso
Veronika Cheplygina
JIANXU CHEN
Evangelia Christodoulou … (voir 59 de plus)
BETH A. CIMINI
Gary S. Collins
Keyvan Farahani
LUCIANA FERRER
Adrian Galdran
Bram van Ginneken
Ben Glocker
PATRICK GODAU
Robert Cary Haase
Daniel A. Hashimoto
Michael M. Hoffman
Merel Huisman
Fabian Isensee
Pierre Jannin
CHARLES E. KAHN
DAGMAR KAINMUELLER
BERNHARD KAINZ
Alexandros Karargyris
Alan Karthikesalingam
H. Kenngott
Jens Kleesiek
Florian Kofler
THIJS KOOI
Annette Kopp-Schneider
Michal Kozubek
Anna Kreshuk
Tahsin Kurc
BENNETT A. LANDMAN
GEERT LITJENS
Amin Madani
Klaus Maier-Hein
Anne L. Martel
Peter Mattson
ERIK MEIJERING
Bjoern Menze
KAREL G.M. MOONS
Henning Müller
Brennan Nichyporuk
Felix Nickel
Jens Petersen
SUSANNE M. RAFELSKI
NASIR RAJPOOT
Mauricio Reyes
MICHAEL A. RIEGLER
Nicola Rieke
Julio Saez-Rodriguez
Clara I. Sánchez
SHRAVYA SHETTY
M. Smeden
Ronald M. Summers
Abdel Aziz Taha
ALEKSEI TIULPIN
Sotirios A. Tsaftaris
Ben Van Calster
Gael Varoquaux
Manuel Wiesenfarth
ZIV R. YANIV
PAUL F. JÄGER
Lena Maier-Hein
2024-02-12
Nature methods (publié)
doi.org
arxiv.org
The Leukemoid Reaction in Severe Alcoholic Hepatitis: A Case Report
Siva Reddy
Sachin Agrawal
Sunil Kumar
Sourya Acharya
2024-02-11
Cureus (publié)
doi.org
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Tara Akhound-Sadegh
Jarrid Rector-Brooks
Joey Bose
Sarthak Mittal
Pablo Lemos
Cheng-Hao Liu
Marcin Sendera
Siamak Ravanbakhsh
Gauthier Gidel
Yoshua Bengio
Nikolay Malkin
Alexander Tong
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-… (voir plus)body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org
Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
Tara Akhound-Sadegh
Jarrid Rector-Brooks
Joey Bose
Sarthak Mittal
Pablo Lemos
Cheng-Hao Liu
Marcin Sendera
Siamak Ravanbakhsh
Gauthier Gidel
Yoshua Bengio
Nikolay Malkin
Alexander Tong
Efficiently generating statistically independent samples from an unnormalized probability distribution, such as equilibrium samples of many-… (voir plus)body systems, is a foundational problem in science. In this paper, we propose Iterated Denoising Energy Matching (iDEM), an iterative algorithm that uses a novel stochastic score matching objective leveraging solely the energy function and its gradient -- and no data samples -- to train a diffusion-based sampler. Specifically, iDEM alternates between (I) sampling regions of high model density from a diffusion-based sampler and (II) using these samples in our stochastic matching objective to further improve the sampler. iDEM is scalable to high dimensions as the inner matching objective, is simulation-free, and requires no MCMC samples. Moreover, by leveraging the fast mode mixing behavior of diffusion, iDEM smooths out the energy landscape enabling efficient exploration and learning of an amortized sampler. We evaluate iDEM on a suite of tasks ranging from standard synthetic energy functions to invariant
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org
Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots
Simon Chamorro
Victor Klemm
Miguel de La Iglesia Valls
Chris Pal
Roland Siegwart
In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across v… (voir plus)arious domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot.
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org
Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots
Simon Chamorro
Victor Klemm
Miguel de La Iglesia Valls
Chris Pal
Roland Siegwart
In recent years, legged and wheeled-legged robots have gained prominence for tasks in environments predominantly created for humans across v… (voir plus)arious domains. One significant challenge faced by many of these robots is their limited capability to navigate stairs, which hampers their functionality in multi-story environments. This study proposes a method aimed at addressing this limitation, employing reinforcement learning to develop a versatile controller applicable to a wide range of robots. In contrast to the conventional velocity-based controllers, our approach builds upon a position-based formulation of the RL task, which we show to be vital for stair climbing. Furthermore, the methodology leverages an asymmetric actor-critic structure, enabling the utilization of privileged information from simulated environments during training while eliminating the reliance on exteroceptive sensors during real-world deployment. Another key feature of the proposed approach is the incorporation of a boolean observation within the controller, enabling the activation or deactivation of a stair-climbing mode. We present our results on different quadrupeds and bipedal robots in simulation and showcase how our method allows the balancing robot Ascento to climb 15cm stairs in the real world, a task that was previously impossible for this robot.
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org
On the Privacy of Selection Mechanisms with Gaussian Noise
Jonathan Lebensold
Doina Precup
Borja Balle
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org
V-STaR: Training Verifiers for Self-Taught Reasoners
Arian Hosseini
Xingdi Yuan
Nikolay Malkin
Aaron Courville
Alessandro Sordoni
Rishabh Agarwal
Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to… (voir plus) improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is used at inference time to select one solution among many candidate solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers, delivering a 4% to 17% test accuracy improvement over existing self-improvement and verification approaches on common code generation and math reasoning benchmarks with LLaMA2 models.
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org
V-STaR: Training Verifiers for Self-Taught Reasoners
Arian Hosseini
Xingdi Yuan
Nikolay Malkin
Aaron Courville
Alessandro Sordoni
Rishabh Agarwal
Common self-improvement approaches for large language models (LLMs), such as STaR (Zelikman et al., 2022), iteratively fine-tune LLMs on sel… (voir plus)f-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is used at inference time to select one solution among many candidate solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers, delivering a 4% to 17% test accuracy improvement over existing self-improvement and verification approaches on common code generation and math reasoning benchmarks with LLaMA2 models.
2024-02-09
ArXiv (prépublication)
doi.org
arxiv.org