Publications

Multi-variable Hard Physical Constraints for Climate Model Downscaling

José Manuel Gutiérrez

Global Climate Models (GCMs) are the primary tool to simulate climate evolution and assess the impacts of climate change. However, they ofte… (see more)n operate at a coarse spatial resolution that limits their accuracy in reproducing local-scale phenomena. Statistical downscaling methods leveraging deep learning offer a solution to this problem by approximating local-scale climate fields from coarse variables, thus enabling regional GCM projections. Typically, climate fields of different variables of interest are downscaled independently, resulting in violations of fundamental physical properties across interconnected variables. This study investigates the scope of this problem and, through an application on temperature, lays the foundation for a framework introducing multi-variable hard constraints that guarantees physical relationships between groups of downscaled climate variables.

2024-01-21

AAAI Symposium Series (published)

doi.org

arxiv.org

RapidBrachyTG43: A Geant4‐based TG‐43 parameter and dose calculation module for brachytherapy dosimetry

Jonathan Kalinowski

S. Enger

2024-01-21

Medical Physics (published)

doi.org

Transnational conservation to anticipate future plant shifts in Europe

Yohann Chauvier-Mendes

Laura J. Pollock

Peter H. Verburg

Dirk N. Karger

Loïc Pellissier

Sébastien Lavergne

Niklaus E. Zimmermann

Wilfried Thuiller

2024-01-21

Nature Ecology & Evolution (published)

doi.org

Deployable Reinforcement Learning with Variable Control Rate

Yong Wang

Giovanni Beltrame

2024-01-16

ArXiv (preprint)

doi.org

arxiv.org

METhodological RadiomICs Score (METRICS): a quality scoring tool for radiomics research endorsed by EuSoMII

Burak Kocak

Tugba Akinci D’Antonoli

Nathaniel Mercaldo

Angel Alberich-Bayarri

Bettina Baessler

Ilaria Ambrosini

Anna E. Andreychenko

Spyridon Bakas

Regina G. H. Beets-Tan

Keno Bressem

Irene Buvat

Roberto Cannella

Luca Alessandro Cappellini

Armando Ugo Cavallo

Leonid L. Chepelev

Linda Chi Hang Chu

Aydin Demircioglu

Nandita M. deSouza

Matthias Dietzel

Salvatore Claudio Fanni … (see 40 more)

Andrey Fedorov

Laure S. Fournier

Valentina Giannini

Rossano Girometti

Kevin B. W. Groot Lipman

Georgios Kalarakis

Brendan S. Kelly

Michail E. Klontzas

Dow-Mu Koh

Elmar Kotter

Ho Yun Lee

Mario Maas

Luis Marti-Bonmati

Henning Müller

Nancy Obuchowski

Fanny Orlhac

Nikolaos Papanikolaou

Ekaterina Petrash

Elisabeth Pfaehler

Daniel Pinto dos Santos

Andrea Ponsiglione

Sebastià Sabater

Francesco Sardanelli

Philipp Seeböck

Nanna M. Sijtsema

Arnaldo Stanzione

Alberto Traverso

Lorenzo Ugga

Martin Vallières

Lisanne V. van Dijk

Joost J. M. van Griethuysen

Robbert W. van Hamersvelt

Peter van Ooijen

Federica Vernuccio

Alan Wang

Stuart Williams

Jan Witowski

Zhongyi Zhang

Alex Zwanenburg

Renato Cuocolo

2024-01-16

Insights into Imaging (published)

doi.org

Abstract B049: Pancreatic beta cell stress pathways drive pancreatic ductal adenocarcinoma development in obesity

Cathy C. Garcia

Aarthi Venkat

Alex Tong

Sherry Agabiti

Lauren Lawres

Rebecca Cardone

Richard G. Kibbey

Smita Krishnaswamy

Mandar Deepak Muzumdar

2024-01-15

Cancer Research (published)

doi.org

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View

Raj Ghugare

Matthieu Geist

Glen Berseth

Benjamin Eysenbach

Some reinforcement learning (RL) algorithms can stitch pieces of experience to solve a task never seen before during training. This oft-soug… (see more)ht property is one of the few ways in which RL methods based on dynamic-programming differ from RL methods based on supervised-learning (SL). Yet, certain RL methods based on off-the-shelf SL algorithms achieve excellent results without an explicit mechanism for stitching; it remains unclear whether those methods forgo this important stitching property. This paper studies this question for the problems of achieving a target goal state and achieving a target return value. Our main result is to show that the stitching property corresponds to a form of combinatorial generalization: after training on a distribution of (state, goal) pairs, one would like to evaluate on (state, goal) pairs not seen together in the training data. Our analysis shows that this sort of generalization is different from i.i.d. generalization. This connection between stitching and generalisation reveals why we should not expect SL-based RL methods to perform stitching, even in the limit of large datasets and models. Based on this analysis, we construct new datasets to explicitly test for this property, revealing that SL-based methods lack this stitching property and hence fail to perform combinatorial generalization. Nonetheless, the connection between stitching and combinatorial generalisation also suggests a simple remedy for improving generalisation in SL: data augmentation. We propose a temporal data augmentation and demonstrate that adding it to SL-based methods enables them to successfully complete tasks not seen together during training. On a high level, this connection illustrates the importance of combinatorial generalization for data efficiency in time-series data beyond tasks beyond RL, like audio, video, or text.

2024-01-15

ICLR.cc/2024/Conference (poster)

doi.org

openreview.net

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

Mingde Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstracti… (see more)ons to generalize better in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and thus enables sparse decision-making and focused computation on the relevant parts of the environment. The decomposition relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guarantees under appropriate assumptions and establish where our approach is expected to be helpful. Generalization-focused experiments validate Skipper's significant advantage in zero-shot generalization, compared to some existing state-of-the-art hierarchical planning methods.

2024-01-15

International Conference on Learning Representations (poster)

doi.org

openreview.net

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

Eduardo Dadalto Câmara Gomes

Marco Romanelli

Georg Pichler

Pablo Piantanida

2024-01-15

ICLR.cc/2024/Conference (poster)

doi.org

openreview.net

Decoupling regularization from the action space

Sobhan Mohammadpour

Emma Frejinger

Pierre-Luc Bacon

Regularized reinforcement learning (RL), particularly the entropy-regularized kind, has gained traction in optimal control and inverse RL. W… (see more)hile standard unregularized RL methods remain unaffected by changes in the number of actions, we show that it can severely impact their regularized counterparts. This paper demonstrates the importance of decoupling the regularizer from the action space: that is, to maintain a consistent level of regularization regardless of how many actions are involved to avoid over-regularization. Whereas the problem can be avoided by introducing a task-specific temperature parameter, it is often undesirable and cannot solve the problem when action spaces are state-dependent. In the state-dependent action context, different states with varying action spaces are regularized inconsistently. We introduce two solutions: a static temperature selection approach and a dynamic counterpart, universally applicable where this problem arises. Implementing these changes improves performance on the DeepMind control suite in static and dynamic temperature regimes and a biological design task.

2024-01-15

ICLR.cc/2024/Conference (poster)

doi.org

openreview.net

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory

Arnab Kumar Mondal

Siba Smarak Panigrahi

Sai Rajeswar

Kaleem Siddiqi

Siamak Ravanbakhsh

The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could adva… (see more)nce Reinforcement Learning (RL) and Planning algorithms, but achieving it is challenging. Inaccuracies in model estimates can compound, resulting in increased errors over long horizons. We approach this problem from the lens of Koopman theory, where the nonlinear dynamics of the environment can be linearized in a high-dimensional latent space. This allows us to efficiently parallelize the sequential problem of long-range prediction using convolution while accounting for the agent's action at every time step. Our approach also enables stability analysis and better control over gradients through time. Taken together, these advantages result in significant improvement over the existing approaches, both in the efficiency and the accuracy of modeling dynamics over extended horizons. We also show that this model can be easily incorporated into dynamics modeling for model-based planning and model-free RL and report promising experimental results.

2024-01-15

International Conference on Learning Representations (poster)

doi.org

openreview.net

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Divyat Mahajan

Ioannis Mitliagkas

Brady Neal

Vasilis Syrgkanis

2024-01-15

ICLR.cc/2024/Conference (spotlight)

openreview.net