Publications

BatchGFN: Generative Flow Networks for Batch Active Learning
Shreshth A Malik
Salem Lahlou
Andrew Jesson
Moksh J. Jain
Nikolay Malkin
Tristan Deleu
Yoshua Bengio
Yarin Gal
We introduce BatchGFN—a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points pro… (see more)portional to a batch reward. With an appropriate reward function to quantify the utility of acquiring a batch, such as the joint mutual information between the batch and the model parameters, BatchGFN is able to construct highly informative batches for active learning in a principled way. We show our approach enables sampling near-optimal utility batches at inference time with a single forward pass per point in the batch in toy regression problems. This alleviates the computational complexity of batch-aware algorithms and removes the need for greedy approximations to find maximizers for the batch reward. We also present early results for amortizing training across acquisition steps, which will enable scaling to real-world tasks.
2023-06-18
ICML.cc/2023/Workshop/SPIGM (poster)
doi.org
openreview.net
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation
Chris Emezue
Alexandre Drouin
Tristan Deleu
Stefan Bauer
Yoshua Bengio
2023-06-18
ICML.cc/2023/Workshop/SPIGM (poster)
doi.org
openreview.net
CAMMARL: Conformal Action Modeling in Multi Agent Reinforcement Learning
Nikunj Gupta
Somjit Nath
S Ebrahimi Kahou
Before taking actions in an environment with more than one intelligent agent, an autonomous agent may benefit from reasoning about the other… (see more) agents and utilizing a notion of a guarantee or confidence about the behavior of the system. In this article, we propose a novel multi-agent reinforcement learning (MARL) algorithm CAMMARL, which involves modeling the actions of other agents in different situations in the form of confident sets, i.e., sets containing their true actions with a high probability. We then use these estimates to inform an agent's decision-making. For estimating such sets, we use the concept of conformal predictions, by means of which, we not only obtain an estimate of the most probable outcome but get to quantify the operable uncertainty as well. For instance, we can predict a set that provably covers the true predictions with high probabilities (e.g., 95%). Through several experiments in two fully cooperative multi-agent tasks, we show that CAMMARL elevates the capabilities of an autonomous agent in MARL by modeling conformal prediction sets over the behavior of other agents in the environment and utilizing such estimates to enhance its policy learning.
2023-06-18
ArXiv (preprint)
doi.org
openreview.net
CATS: A Computation-Aware Transaction Processing System with Proactive Unlocking
Bolun Zhu
Yu Hua
Ziyin Long
Xue Liu
With the increasing complexity of network applications and high demands for QoS, transaction processing systems have received more attention… (see more)s due to salient features of simplicity and atomicity. Computation operations play an important role in transaction processing systems. However, conventional QoS-based mechanisms become inefficient due to the limited concurrent support upon computation operations, thus causing high time consumption in the critical path of concurrency control. In order to efficiently offer concurrent computations, we propose CATS, a Computation Aware Transaction processing System, to mitigate performance impacts caused by computation operations. CATS further leverages program semantics to defer the execution of transaction operations in the commit phase to alleviate unnecessary conflicts caused by computations. Extensive evaluation results demonstrate that CATS significantly outperforms state-of-the-art designs, including 2PL and OCC based transaction processing systems on high-contended and computation-intensive workloads. We have released the open-source codes in GitHub for public use.
2023-06-18
2023 IEEE/ACM 31st International Symposium on Quality of Service (IWQoS) (published)
doi.org
Causal Discovery with Language Models as Imperfect Experts
Stephanie Long
Alexandre Piché
Valentina Zantedeschi
Tibor Schuster
Alexandre Drouin
Understanding the causal relationships that underlie a system is a fundamental prerequisite to accurate decision-making. In this work, we ex… (see more)plore how expert knowledge can be used to improve the data-driven identification of causal graphs, beyond Markov equivalence classes. In doing so, we consider a setting where we can query an expert about the orientation of causal relationships between variables, but where the expert may provide erroneous information. We propose strategies for amending such expert knowledge based on consistency properties, e.g., acyclicity and conditional independencies in the equivalence class. We then report a case study, on real data, where a large language model is used as an imperfect expert.
2023-06-18
ICML.cc/2023/Workshop/SPIGM (poster)
doi.org
openreview.net
Development of a hydrated electron dosimeter for radiotherapy applications: A proof of concept.
Julien Mégrourèche
H. Bekerat
Jingyi Bian
Alaina Bui
Jack C Sankey
Lilian Childress
S. Enger
BACKGROUND Hydrated electrons, which are short-lived products of radiolysis in water, increase the optical absorption of water, providing a … (see more)pathway toward near-tissue-equivalent clinical radiation dosimeters. This has been demonstrated in high-dose-per-pulse radiochemistry research, but, owing to the weak absorption signal, its application in existing low-dose-per-pulse radiotherapy provided by clinical linear accelerators (linacs) has yet to be investigated. PURPOSE The aims of this study were to measure the optical absorption associated with hydrated electrons produced by clinical linacs and to assess the suitability of the technique for radiotherapy (⩽ 1 cGy per pulse) applications. METHODS 40 mW of 660-nm laser light was sent five passes through deionized water contained in a 10 × 4 ×
2023-06-18
Medical Physics (published)
doi.org
An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets
Nikhil Murali Vemgal
Elaine Lau
Doina Precup
Reinforcement Learning (RL) algorithms aim to learn an optimal policy by iteratively sampling actions to learn how to maximize the total exp… (see more)ected return,
2023-06-18
ICML.cc/2023/Workshop/SPIGM (poster)
doi.org
openreview.net
Exploring Exchangeable Dataset Amortization for Bayesian Posterior Inference
Sarthak Mittal
Niels Leif Bracher
Guillaume Lajoie
Priyank Jaini
Marcus A Brubaker
Bayesian inference provides a natural way of incorporating uncertainties and different underlying theories when making predictions or analyz… (see more)ing complex systems. However, it requires computationally expensive routines for approximation, which have to be re-run when new data is observed and are thus infeasible to efficiently scale and reuse. In this work, we look at the problem from the perspective of amortized inference to obtain posterior parameter distributions for known probabilistic models. We propose a neural network-based approach that can handle exchangeable observations and amortize over datasets to convert the problem of Bayesian posterior inference into a single forward pass of a network. Our empirical analyses explore various design choices for amortized inference by comparing: (a) our proposed variational objective with forward KL minimization, (b) permutation-invariant architectures like Transformers and DeepSets, and (c) parameterizations of posterior families like diagonal Gaussian and Normalizing Flows. Through our experiments, we successfully apply amortization techniques to estimate the posterior distributions for different domains solely through inference.
2023-06-18
ICML.cc/2023/Workshop/SPIGM (poster)
openreview.net
openreview.net
Green Federated Learning
Ashkan Yousefpour
Shen Guo
Ashish Shenoy
Sayan Ghosh
Pierre Stock
Kiwan Maeng
Schalk-Willem Kruger
Michael G. Rabbat
Carole-Jean Wu
Ilya Mironov
2023-06-18
ICML.cc/2023/Workshop/FL (published)
openreview.net
openreview.net
A Kernel Perspective on Behavioural Metrics for Markov Decision Processes
Pablo Samuel Castro
Tyler Kastner
Prakash Panangaden
Mark Rowland
We present a novel perspective on behavioural metrics for Markov decision processes via the use of positive definite kernels. We define a ne… (see more)w metric under this lens that is provably equivalent to the recently introduced MICo distance (Castro et al., 2021). The kernel perspective enables us to provide new theoretical results, including value-function bounds and low-distortion finite-dimensional Euclidean embeddings, which are crucial when using behavioural metrics for reinforcement learning representations. We complement our theory with strong empirical results that demonstrate the effectiveness of these methods in practice.
2023-06-18
TMLR (accepted)
doi.org
openreview.net
Learning with Learning Awareness using Meta-Values
Tim Cooijmans
Milad Aghajohari
Aaron Courville
2023-06-18
ICML.cc/2023/Workshop/Frontiers4LCD (published)
openreview.net
openreview.net
Online Dynamic Submodular Optimization
Antoine Lesage-Landry
Julien Pallage
We propose new algorithms with provable performance for online binary optimization subject to general constraints and in dynamic settings. W… (see more)e consider the subset of problems in which the objective function is submodular. We propose the online submodular greedy algorithm (OSGA) which solves to optimality an approximation of the previous round loss function to avoid the NP-hardness of the original problem. We extend OSGA to a generic approximation function. We show that OSGA has a dynamic regret bound similar to the tightest bounds in online convex optimization with respect to the time horizon and the cumulative round optimum variation. For instances where no approximation exists or a computationally simpler implementation is desired, we design the online submodular projected gradient descent (OSPGD) by leveraging the Lova\'sz extension. We obtain a regret bound that is akin to the conventional online gradient descent (OGD). Finally, we numerically test our algorithms in two power system applications: fast-timescale demand response and real-time distribution network reconfiguration.
2023-06-18
ArXiv (preprint)
doi.org
arxiv.org