Publications

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
Jo˜ao Monteiro
Étienne Marcotte
Pierre-Andre Noel
Valentina Zantedeschi
David Vazquez
Nicolas Chapados
Chris Pal
Perouz Taslakian
In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference informati… (see more)on. Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention operations, and caching is desirable. However, caching transformer states can easily require almost as much space as the model parameters. When the right context isn't known in advance, caching ICL can be challenging. This work addresses these limitations by introducing models that, inspired by the encoder-decoder architecture, use cross-attention to condition generation on reference text without the prompt. More precisely, we leverage pre-trained decoder-only models and only train a small number of added layers. We use Question-Answering (QA) as a testbed to evaluate the ability of our models to perform conditional generation and observe that they outperform ICL, are comparable to fine-tuned prompted LLMs, and drastically reduce the space footprint relative to standard KV caching by two orders of magnitude.
2024-04-23
ArXiv (preprint)
doi.org
arxiv.org
Fairness Incentives in Response to Unfair Dynamic Pricing
Jesse Thibodeau
Hadi Nekoei
Afaf Taïk
Janarthanan Rajendran
Golnoosh Farnadi
The use of dynamic pricing by profit-maximizing firms gives rise to demand fairness concerns, measured by discrepancies in consumer groups' … (see more)demand responses to a given pricing strategy. Notably, dynamic pricing may result in buyer distributions unreflective of those of the underlying population, which can be problematic in markets where fair representation is socially desirable. To address this, policy makers might leverage tools such as taxation and subsidy to adapt policy mechanisms dependent upon their social objective. In this paper, we explore the potential for AI methods to assist such intervention strategies. To this end, we design a basic simulated economy, wherein we introduce a dynamic social planner (SP) to generate corporate taxation schedules geared to incentivizing firms towards adopting fair pricing behaviours, and to use the collected tax budget to subsidize consumption among underrepresented groups. To cover a range of possible policy scenarios, we formulate our social planner's learning problem as a multi-armed bandit, a contextual bandit and finally as a full reinforcement learning (RL) problem, evaluating welfare outcomes from each case. To alleviate the difficulty in retaining meaningful tax rates that apply to less frequently occurring brackets, we introduce FairReplayBuffer, which ensures that our RL agent samples experiences uniformly across a discretized fairness space. We find that, upon deploying a learned tax and redistribution policy, social welfare improves on that of the fairness-agnostic baseline, and approaches that of the analytically optimal fairness-aware baseline for the multi-armed and contextual bandit settings, and surpassing it by 13.19% in the full RL setting.
2024-04-22
ArXiv (preprint)
doi.org
arxiv.org
Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey
Maeva Guerrier
Hassan Fouad
Giovanni Beltrame
Reinforcement learning is a powerful technique for developing new robot behaviors. However, typical lack of safety guarantees constitutes a … (see more)hurdle for its practical application on real robots. To address this issue, safe reinforcement learning aims to incorporate safety considerations, enabling faster transfer to real robots and facilitating lifelong learning. One promising approach within safe reinforcement learning is the use of control barrier functions. These functions provide a framework to ensure that the system remains in a safe state during the learning process. However, synthesizing control barrier functions is not straightforward and often requires ample domain knowledge. This challenge motivates the exploration of data-driven methods for automatically defining control barrier functions, which is highly appealing. We conduct a comprehensive review of the existing literature on safe reinforcement learning using control barrier functions. Additionally, we investigate various techniques for automatically learning the Control Barrier Functions, aiming to enhance the safety and efficacy of Reinforcement Learning in practical robot applications.
2024-04-22
ArXiv (preprint)
doi.org
arxiv.org
Foliar spectra accurately distinguish most temperate tree species and show strong phylogenetic signal
Florence Blanchard
Anne Bruneau
Étienne Laliberté
2024-04-20
American-Eurasian journal of botany (published)
doi.org
BACS: Background Aware Continual Semantic Segmentation
Mostafa ElAraby
Ali Harakeh
Liam Paull
Semantic segmentation plays a crucial role in enabling comprehensive scene understanding for robotic systems. However, generating annotation… (see more)s is challenging, requiring labels for every pixel in an image. In scenarios like autonomous driving, there's a need to progressively incorporate new classes as the operating environment of the deployed agent becomes more complex. For enhanced annotation efficiency, ideally, only pixels belonging to new classes would be annotated. This approach is known as Continual Semantic Segmentation (CSS). Besides the common problem of classical catastrophic forgetting in the continual learning setting, CSS suffers from the inherent ambiguity of the background, a phenomenon we refer to as the"background shift'', since pixels labeled as background could correspond to future classes (forward background shift) or previous classes (backward background shift). As a result, continual learning approaches tend to fail. This paper proposes a Backward Background Shift Detector (BACS) to detect previously observed classes based on their distance in the latent space from the foreground centroids of previous steps. Moreover, we propose a modified version of the cross-entropy loss function, incorporating the BACS detector to down-weight background pixels associated with formerly observed classes. To combat catastrophic forgetting, we employ masked feature distillation alongside dark experience replay. Additionally, our approach includes a transformer decoder capable of adjusting to new classes without necessitating an additional classification head. We validate BACS's superior performance over existing state-of-the-art methods on standard CSS benchmarks.
2024-04-19
ArXiv (preprint)
doi.org
arxiv.org
Categorical Generative Model Evaluation via Synthetic Distribution Coarsening
Florence Regol
Mark Coates
As we expect to see a rapid integration of generative models in our day to day lives, the development of rigorous methods of evaluation and … (see more)analysis for generative models has never been more pressing. Multiple works have highlighted the shortcomings of widely used metrics and exposed how they fail to behave as expected in some settings. So far, the response has been to use a variety of metrics that target different desirable and interpretable properties such as fidelity, diversity, and authenticity, to obtain a clearer picture of a generative model’s capabilities. These methods mainly focus on ordinal data and they all suffer from the same unavoidable issues stemming from estimating quantities of high-dimensional data from a limited number of samples. We propose to take an alternative approach and to return to the synthetic data setting where the ground truth is explicit and known. We focus on nominal categorical data and introduce an evaluation method that can scale to the high-dimensional settings often encountered in practice. Our method involves successively binning the large space to obtain smaller probability spaces and coarser distributions where meaningful statistical estimates can be obtained. This allows us to provide probabilistic guarantees and sample complexities and we illustrate how our method can be applied to distinguish between the capabilities of several state-of-the-art categorical models.
2024-04-18
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
Conditions on Preference Relations that Guarantee the Existence of Optimal Policies
Jonathan Colaco Carr
Prakash Panangaden
Doina Precup
2024-04-18
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
doi.org
arxiv.org
Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias
Yu Yang
Eric Gan
Gintare Karolina Dziugaite
Baharan Mirzasoleiman
Neural networks trained with (stochastic) gradient descent have an inductive bias towards learning simpler solutions. This makes them highly… (see more) prone to learning spurious correlations in the training data, that may not hold at test time. In this work, we provide the first theoretical analysis of the effect of simplicity bias on learning spurious correlations. Notably, we show that examples with spurious features are provably separable based on the model's output early in training. We further illustrate that if spurious features have a small enough noise-to-signal ratio, the network's output on the majority of examples is almost exclusively determined by the spurious features, leading to poor worst-group test accuracy. Finally, we propose SPARE, which identifies spurious correlations early in training and utilizes importance sampling to alleviate their effect. Empirically, we demonstrate that SPARE outperforms state-of-the-art methods by up to 21.1% in worst-group accuracy, while being up to 12x faster. We also show that SPARE is a highly effective but lightweight method to discover spurious correlations.
2024-04-18
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
doi.org
openreview.net
Introducing v0.5 of the AI Safety Benchmark from MLCommons
Bertie Vidgen
Adarsh Agrawal
Ahmed M. Ahmed
Victor Akinwande
Namir Al-nuaimi
Najla Alfaraj
Elie Alhajjar
Lora Aroyo
Trupti Bavalatti
Borhane Blili-Hamelin
K. Bollacker
Rishi Bomassani
Marisa Ferrara Boston
Sim'eon Campos
Kal Chakra
Canyu Chen
Cody Coleman
Zacharie Delpierre Coudert
Leon Strømberg Derczynski
Debojyoti Dutta … (see 77 more)
Ian Eisenberg
James R. Ezick
Heather Frase
Brian Fuller
Ram Gandikota
Agasthya Gangavarapu
Ananya Gangavarapu
James Gealy
Rajat Ghosh
James Goel
Usman Gohar
Sujata Goswami
Scott A. Hale
Wiebke Hutiri
Joseph Marvin Imperial
Surgan Jandial
Nicholas C. Judd
Felix Juefei-Xu
Foutse Khomh
Bhavya Kailkhura
Hannah Rose Kirk
Kevin Klyman
Chris Knotz
Michael Kuchnik
Shachi H. Kumar
Chris Lengerich
Bo Li
Zeyi Liao
Eileen Peters Long
Victor Lu
Yifan Mai
Priyanka Mary Mammen
Kelvin Manyeki
Sean McGregor
Virendra Mehta
Shafee Mohammed
Emanuel Moss
Lama Nachman
Dinesh Jinenhally Naganna
Amin Nikanjam
Besmira Nushi
Luis Oala
Iftach Orr
Alicia Parrish
Çigdem Patlak
William Pietri
Forough Poursabzi-Sangdeh
Eleonora Presani
Fabrizio Puletti
Paul Rottger
Saurav Sahay
Tim Santos
Nino Scherrer
Alice Schoenauer Sebag
Patrick Schramowski
Abolfazl Shahbazi
Vin Sharma
Xudong Shen
Vamsi Sistla
Leonard Tang
Davide Testuggine
Vithursan Thangarasa
Elizabeth A Watkins
Rebecca Weiss
Christoper A. Welty
Tyler Wilbers
Adina Williams
Carole-Jean Wu
Poonam Yadav
Xianjun Yang
Yi Zeng
Wenhui Zhang
Fedor Zhdanov
Jiacheng Zhu
Percy Liang
Peter Mattson
Joaquin Vanschoren
2024-04-18
ArXiv (preprint)
doi.org
arxiv.org
On learning history-based policies for controlling Markov decision processes
Gandharv Patil
Aditya Mahajan
Doina Precup
2024-04-18
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
doi.org
openreview.net
Length independent PAC-Bayes bounds for Simple RNNs
Volodimir Mitarchuk
Clara Lacroce
Rémi Eyraud
Rémi Emonet
Amaury Habrard
Guillaume Rabusseau
2024-04-18
Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (published)
proceedings.mlr.press
Multi-phase black-hole feedback and a bright [CII] halo in a Lo-BAL quasar at $z\sim6.6$
Manuela Bischetti
Hyunseop Choi
Fabrizio Fiore
Chiara Feruglio
Stefano Carniani
Valentina D'Odorico
Eduardo Banados
Huanqing Chen
Roberto Decarli
Simona Gallerani
Julie Hlavacek-larrondo
Samuel Lai
K. Leighly
Chiara Mazzucchelli
Laurence Perreault-Levasseur
Roberta Tripodi
Fabian Walter
Feige Wang
Jinyi Yang
Maria Vittoria Zanchettin … (see 1 more)
Yongda Zhu
2024-04-18
ArXiv (preprint)
doi.org
arxiv.org