Publications

A Tweedie Compound Poisson Model in Reproducing Kernel Hilbert Space
Yi Lian
Archer Yang
Boxiang Wang
Peng Shi
Robert William Platt
Abstract Tweedie models can be used to analyze nonnegative continuous data with a probability mass at zero. There have been wide application… (voir plus)s in natural science, healthcare research, actuarial science, and other fields. The performance of existing Tweedie models can be limited on today’s complex data problems with challenging characteristics such as nonlinear effects, high-order interactions, high-dimensionality and sparsity. In this article, we propose a kernel Tweedie model, Ktweedie, and its sparse variant, SKtweedie, that can simultaneously address the above challenges. Specifically, nonlinear effects and high-order interactions can be flexibly represented through a wide range of kernel functions, which is fully learned from the data; In addition, while the Ktweedie can handle high-dimensional data, the SKtweedie with integrated variable selection can further improve the interpretability. We perform extensive simulation studies to justify the prediction and variable selection accuracy of our method, and demonstrate the applications in ratemaking and loss-reserving in general insurance. Overall, the Ktweedie and SKtweedie outperform existing Tweedie models when there exist nonlinear effects and high-order interactions, particularly when the dimensionality is high relative to the sample size. The model is implemented in an efficient and user-friendly R package ktweedie (https://cran.r-project.org/package=ktweedie).
2022-12-12
Technometrics (publié)
doi.org
Detection and genomic analysis of BRAF fusions in Juvenile Pilocytic Astrocytoma through the combination and integration of multi-omic data
Melissa Zwaig
Audrey Baguette
Bo Hu
Michael Johnston
Hussein Lakkis
Emily M. Nakada
Damien Faury
Nikoleta Juretic
Benjamin Ellezam
Alexandre G. Weil
Jason Karamchandani
Jacek Majewski
Mathieu Blanchette
Michael D. Taylor
Marco Gallo
Claudia L. Kleinman
Nada Jabado
Jiannis Ragoussis
Juvenile Pilocytic Astrocytomas (JPAs) are one of the most common pediatric brain tumors, and they are driven by aberrant activation of the … (voir plus)mitogen-activated protein kinase (MAPK) signaling pathway. RAF-fusions are the most common genetic alterations identified in JPAs, with the prototypical KIAA1549-BRAF fusion leading to loss of BRAF’s auto-inhibitory domain and subsequent constitutive kinase activation. JPAs are highly vascular and show pervasive immune infiltration, which can lead to low tumor cell purity in clinical samples. This can result in gene fusions that are difficult to detect with conventional omics approaches including RNA-Seq. To this effect, we applied RNA-Seq as well as linked-read whole-genome sequencing and in situ Hi-C as new approaches to detect and characterize low-frequency gene fusions at the genomic, transcriptomic and spatial level. Integration of these datasets allowed the identification and detailed characterization of two novel BRAF fusion partners, PTPRZ1 and TOP2B, in addition to the canonical fusion with partner KIAA1549. Additionally, our Hi-C datasets enabled investigations of 3D genome architecture in JPAs which showed a high level of correlation in 3D compartment annotations between JPAs compared to other pediatric tumors, and high similarity to normal adult astrocytes. We detected interactions between BRAF and its fusion partners exclusively in tumor samples containing BRAF fusions. We demonstrate the power of integrating multi-omic datasets to identify low frequency fusions and characterize the JPA genome at high resolution. We suggest that linked-reads and Hi-C could be used in clinic for the detection and characterization of JPAs.
2022-12-11
BMC Cancer (publié)
doi.org
Galaxies on graph neural networks: towards robust synthetic galaxy catalogs with deep generative models
Yesukhei Jagvaral
François Lanusse
Sukhdeep Singh
Rachel Mandelbaum
Siamak Ravanbakhsh
Duncan Campbell
The future astronomical imaging surveys are set to provide precise constraints on cosmological parameters, such as dark energy. However, pro… (voir plus)-duction of synthetic data for these surveys, to test and validate analysis methods, suffers from a very high computational cost. In particular, generating mock galaxy catalogs at sufficiently large volume and high resolution will soon become computa-tionally unreachable. In this paper, we address this problem with a Deep Generative Model to create robust mock galaxy catalogs that may be used to test and develop the analysis pipelines of future weak lensing surveys. We build our model on a custom built Graph Convolutional Networks, by placing each galaxy on a graph node and then connecting the graphs within each gravitationally bound system. We train our model on a cosmological simulation with realistic galaxy populations to capture the 2D and 3D orientations of galaxies. The samples from the model exhibit comparable statistical properties to those in the simulations. To the best of our knowledge, this is the first instance of a generative model on graphs in an astrophysical/cosmological context.
2022-12-10
ArXiv (prépublication)
arxiv.org
arxiv.org
Neural Bandits for Data Mining: Searching for Dangerous Polypharmacy
Alexandre Larouche
Audrey Durand
Richard Khoury
Caroline Sirois
2022-12-09
ArXiv (prépublication)
doi.org
arxiv.org
Bayesian Q-learning With Imperfect Expert Demonstrations
Fengdi Che
Xiru Zhu
Doina Precup
David Meger
Gregory Dudek
Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expe… (voir plus)rt information. We propose a novel algorithm to speed up Q-learning with the help of a limited amount of imperfect expert demonstrations. The algorithm avoids excessive reliance on expert data by relaxing the optimal expert assumption and gradually reducing the usage of uninformative expert data. Experimentally, we evaluate our approach on a sparse-reward chain environment and six more complicated Atari games with delayed rewards. With the proposed methods, we can achieve better results than Deep Q-learning from Demonstrations (Hester et al., 2017) in most environments.
2022-12-08
NeurIPS.cc/2022/Workshop/DeepRL (accepté)
doi.org
openreview.net
Energy efficiency as a normative account for predictive coding
Shahab Bakhtiari
2022-12-08
Patterns (publié)
doi.org
Imitation from Observation With Bootstrapped Contrastive Learning
Medric Sonwa
Johanna Hansen
Eugene Belilovsky
2022-12-08
NeurIPS.cc/2022/Workshop/DeepRL (inconnu)
doi.org
openreview.net
Implicit Offline Reinforcement Learning via Supervised Learning
Alexandre Piché
Rafael Pardinas
David Vázquez
Igor Mordatch
Christopher Pal
Offline Reinforcement Learning (RL) via Supervised Learning is a simple and effective way to learn robotic skills from a dataset of varied b… (voir plus)ehaviors. It is as simple as supervised learning and Behavior Cloning (BC) but takes advantage of the return information. On BC tasks, implicit models have been shown to match or outperform explicit ones. Despite the benefits of using implicit models to learn robotic skills via BC, Offline RL via Supervised Learning algorithms have been limited to explicit models. We show how implicit models leverage return information and match or outperform explicit algorithms to acquire robotic skills from fixed datasets. Furthermore, we show how closely related our implicit methods are to other popular RL via Supervised Learning algorithms.
2022-12-08
NeurIPS.cc/2022/Workshop/DeepRL (inconnu)
doi.org
openreview.net
Informing the development of an outcome set and banks of items to measure mobility among individuals with acquired brain injury using natural language processing
Rehab Alhasani
Mathieu Godbout
Audrey Durand
Claudine Auger
Anouk Lamontagne
Sara Ahmed
The banks of items of mobility domains represent a first step toward establishing a comprehensive outcome set and a common language of mobil… (voir plus)ity to develop the ontology. It enables researchers and healthcare professionals to begin exposing the content of mobility measures as a way to assess mobility comprehensively.
2022-12-08
BMC Neurology (publié)
doi.org
Learning Successor Feature Representations to Train Robust Policies for Multi-task Learning
Melissa Mozifian
Dieter Fox
David Meger
Fabio Ramos
Animesh Garg
The deep reinforcement learning (RL) framework has shown great promise to tackle sequential decision-making problems, where the agent learns… (voir plus) to behave optimally through interactions with the environment and receiving rewards. The ability of an RL agent to learn different reward functions concurrently has many benefits, such as the decomposition of task rewards and promoting skill reuse. In this paper, we consider the problem of continuous control for robot manipulation tasks with an explicit representation that promotes skill reuse while learning multiple tasks with similar reward functions. Our approach relies on two key concepts: successor features (SFs), a value function representation that decouples the dynamics of the environment from the rewards, and an actor-critic framework that incorporates the learned SFs representation. SFs form a natural bridge between model-based and model-free RL methods. We first show how to learn a decomposable representation required by SFs as a pre-training stage. The proposed architecture is able to learn decoupled state and reward feature representations for non-linear reward functions. We then evaluate the feasibility of integrating SFs into an actor-critic framework, which is more tailored for tasks solved with deep RL algorithms. The approach is empirically tested on non-trivial continuous control problems with compositional structure built into the reward functions of the tasks.
2022-12-08
NeurIPS.cc/2022/Workshop/DeepRL (inconnu)
openreview.net
openreview.net
Locally Constrained Representations in Reinforcement Learning
Somjit Nath
S Ebrahimi Kahou
The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the enviro… (voir plus)nment. In most cases, the representations learned purely by the reinforcement learning loss can differ vastly across states depending on how the value functions change. However, the representations learned need not be very specific to the task at hand. Relying only on the RL objective may yield representations that vary greatly across successive time steps. In addition, since the RL loss has a changing target, the representations learned would depend on how good the current values/policies are. Thus, disentangling the representations from the main task would allow them to focus not only on the task-specific features but also the environment dynamics. To this end, we propose locally constrained representations, where an auxiliary loss forces the state representations to be predictable by the representations of the neighboring states. This encourages the representations to be driven not only by the value/policy learning but also by an additional loss that constrains the representations from over-fitting to the value loss. We evaluate the proposed method on several known benchmarks and observe strong performance. Especially in continuous control tasks, our experiments show a significant performance improvement.
2022-12-08
NeurIPS.cc/2022/Workshop/DeepRL (inconnu)
doi.org
openreview.net
Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning
Ali Rahimi-Kalahroudi
Janarthanan Rajendran
Ida Momennejad
Harm van Seijen
Sarath Chandar
One of the key behavioral characteristics used in neuroscience to determine whether the subject of study -- be it a rodent or a human -- exh… (voir plus)ibits model-based learning is effective adaptation to local changes in the environment, a particular form of adaptivity that is the focus of this work. In reinforcement learning, however, recent work has shown that modern deep model-based reinforcement-learning (MBRL) methods adapt poorly to local environment changes. An explanation for this mismatch is that MBRL methods are typically designed with sample-efficiency on a single task in mind and the requirements for effective adaptation are substantially higher, both in terms of the learned world model and the planning routine. One particularly challenging requirement is that the learned world model has to be sufficiently accurate throughout relevant parts of the state-space. This is challenging for deep-learning-based world models due to catastrophic forgetting. And while a replay buffer can mitigate the effects of catastrophic forgetting, the traditional first-in-first-out replay buffer precludes effective adaptation due to maintaining stale data. In this work, we show that a conceptually simple variation of this traditional replay buffer is able to overcome this limitation. By removing only samples from the buffer from the local neighbourhood of the newly observed samples, deep world models can be built that maintain their accuracy across the state-space, while also being able to effectively adapt to local changes in the reward function. We demonstrate this by applying our replay-buffer variation to a deep version of the classical Dyna method, as well as to recent methods such as PlaNet and DreamerV2, demonstrating that deep model-based methods can adapt effectively as well to local changes in the environment.
2022-12-08
NeurIPS.cc/2022/Workshop/DeepRL (accepté)
doi.org
proceedings.mlr.press