Publications

Surface water temperature observations and ice phenology estimations for 1.4 million lakes globally
Maartje C. Korver
Bernhard Lehner
Jeffrey A. Cardille
Laura Carrea
2024-06-30
Remote Sensing of Environment (published)
doi.org
The Position Dependence of Electron Beam Induced Effects in 2D Materials with Deep Neural Networks
Kevin M. Roccapriore
Max Schwarzer
Joshua Greaves
Jesse Farebrother
Riccardo Torsi
Rishabh Agarwal
Colton Bishop
Igor Mordatch
Ekin D. Cubuk
Aaron Courville
Bellemare Marc-Emmanuel
Joshua Robinson
Pablo Samuel Castro
Sergei V Kalinin
2024-06-30
Microscopy and Microanalysis (unknown)
doi.org
Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems extended abstract
Tomas Gonzalez
Cristobal Guzman
Courtney Paquette
2024-06-29
Proceedings of Thirty Seventh Conference on Learning Theory (published)
proceedings.mlr.press
proceedings.mlr.press
Variable Time Step Reinforcement Learning for Robotic Applications
Yong Wang
Giovanni Beltrame
Traditional reinforcement learning (RL) generates discrete control policies, assigning one action per cycle. These policies are usually impl… (see more)emented as in a fixed-frequency control loop. This rigidity presents challenges as optimal control frequency is task-dependent; suboptimal frequencies increase computational demands and reduce exploration efficiency. Variable Time Step Reinforcement Learning (VTS-RL) addresses these issues with adaptive control frequencies, executing actions only when necessary, thus reducing computational load and extending the action space to include action durations. In this paper we introduce the Multi-Objective Soft Elastic Actor-Critic (MOSEAC) method to perform VTS-RL, validating it through theoretical analysis and experimentation in simulation and on real robots. Results show faster convergence, better training results, and reduced energy consumption with respect to other variable- or fixed-frequency approaches.
2024-06-28
ArXiv (preprint)
doi.org
arxiv.org
Adversarial Training with Synthesized Data: A Path to Robust and Generalizable Neural Networks
Reza Bayat
Irina Rish
Adversarial Training (AT) is a well-known framework designed to mitigate adversarial vulnerabilities in neural networks. Recent research ind… (see more)icates that incorporating adversarial examples (AEs) in training can enhance models' generalization capabilities. To understand the impact of AEs on learning dynamics, we study AT through the lens of sample difficulty methodologies. Our findings show that AT leads to more stable learning dynamics compared to Natural Training (NT), resulting in gradual performance improvements and less overconfident predictions. This suggests that AT steers training away from learning easy, perturbable spurious features toward more resilient and generalizable ones. However, a trade-off exists between adversarial robustness and generalization gains, due to robust overfitting, limiting practical deployment. To address this, we propose using synthesized data to bridge this gap. Our results demonstrate that AT benefits significantly from synthesized data, whereas NT does not, enhancing generalization without compromising robustness and offering new avenues for developing robust and generalizable models.
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
openreview.net
openreview.net
Decomposed evaluations of geographic disparities in text-to-image models
Abhishek Sureddy
Dishant Padalia
Nandhinee Periyakaruppan
Oindrila Saha
Adina Williams
Adriana Romero
Megan Richards
Polina Kirichenko
Melissa Hall
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
doi.org
openreview.net
Economic evaluation of the effect of needle and syringe programs on skin, soft tissue, and vascular infections in people who inject drugs: a microsimulation modelling approach
Jihoon Lim
W. Alton Russell
Mariam El-Sheikh
David L. Buckeridge
Dimitra Panagiotoglou
Needle and syringe programs (NSP) are effective harm-reduction strategies against HIV and hepatitis C. Although skin, soft tissue, and vascu… (see more)lar infections (SSTVI) are the most common morbidities in people who inject drugs (PWID), the extent to which NSP are clinically and cost-effective in relation to SSTVI in PWID remains unclear. The objective of this study was to model the clinical- and cost-effectiveness of NSP with respect to treatment of SSTVI in PWID. We performed a model-based, economic evaluation comparing a scenario with NSP to a scenario without NSP. We developed a microsimulation model to generate two cohorts of 100,000 individuals corresponding to each NSP scenario and estimated quality-adjusted life-years (QALY) and cost (in 2022 Canadian dollars) over a 5-year time horizon (1.5% per annum for costs and outcomes). To assess the clinical effectiveness of NSP, we conducted survival analysis that accounted for the recurrent use of health care services for treating SSTVI and SSTVI mortality in the presence of competing risks. The incremental cost-effectiveness ratio associated with NSP was
2024-06-27
Harm Reduction Journal (published)
doi.org
In-Context Learning, Can It Break Safety?
Sophie Xhonneux
David Dobre
Michael Noukhovitch
Jian Tang
Gauthier Gidel
Dhanya Sridhar
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
openreview.net
openreview.net
Predicting the Population Risk of Suicide Using Routinely Collected Health Administrative Data in Quebec, Canada: Model-Based Synthetic Estimation Study
JianLi Wang
Fatemeh Gholi Zadeh Kharrat
Geneviève Gariépy
Christian Gagné
Jean-François Pelletier
Victoria Massamba
Pascale Lévesque
Mada Mohammed
Alain Lesage
2024-06-27
JMIR Public Health and Surveillance (published)
doi.org
A Randomized Controlled Simulation Trial of a Neonatal Resuscitation Digital Game Simulator for Labour and Delivery Room Staff
Christiane Bilodeau
Georg M. Schmölzer
Maria Cutumisu
2024-06-27
Children (published)
doi.org
Robust Knowledge Unlearning via Mechanistic Localizations
Phillip Huang Guo
Aaquib Syed
Abhay Sheshadri
Aidan Ewart
Gintare Karolina Dziugaite
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
openreview.net
openreview.net
Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
Rishika Bhagwatkar
Shravan Nayak
Reza Bayat
Alexis Roger
Daniel Z Kaplan
Pouya Bashivan
Irina Rish
Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications. However, as they becoming increasingly pr… (see more)evalent, ensuring their robustness against adversarial attacks is paramount. This work systematically investigates the impact of model design choices on the adversarial robustness of VLMs against image-based attacks. Additionally, we introduce novel, cost-effective approaches to enhance robustness through prompt formatting. By rephrasing questions and suggesting potential adversarial perturbations, we demonstrate substantial improvements in model robustness against strong image-based attacks such as Auto-PGD. Our findings provide important guidelines for developing more robust VLMs, particularly for deployment in safety-critical environments.
2024-06-27
ICML.cc/2024/Workshop/NextGenAISafety (poster)
doi.org
openreview.net