Search Results for author: Irina Rish

Found 63 papers, 25 papers with code

LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression

no code implementations25 Sep 2023 Ayush Kaushal, Tejas Vaidhya, Irina Rish

Low Rank Decomposition of matrix - splitting a large matrix into a product of two smaller matrix offers a means for compression that reduces the parameters of a model without sparsification, and hence delivering more speedup on modern hardware.

Code Generation Quantization

Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning

no code implementations19 Sep 2023 Mohammad-Javad Darvishi-Bayazi, Mohammad Sajjad Ghaemi, Timothee Lesort, Md Rifat Arefin, Jocelyn Faubert, Irina Rish

We see improvement in the performance of the target model on the target (NMT) datasets by using the knowledge from the source dataset (TUAB) when a low amount of labelled data was available.


Continual Pre-Training of Large Language Models: How to (re)warm your model?

1 code implementation8 Aug 2023 Kshitij Gupta, Benjamin Thérien, Adam Ibrahim, Mats L. Richter, Quentin Anthony, Eugene Belilovsky, Irina Rish, Timothée Lesort

We study the warmup phase of models pre-trained on the Pile (upstream data, 300B tokens) as we continue to pre-train on SlimPajama (downstream data, 297B tokens), following a linear warmup and cosine decay schedule.

Language Modelling

Effective Latent Differential Equation Models via Attention and Multiple Shooting

no code implementations11 Jul 2023 Germán Abrevaya, Mahta Ramezanian-Panahi, Jean-Christophe Gagnon-Audet, Pablo Polosecki, Irina Rish, Silvina Ponce Dawson, Guillermo Cecchi, Guillaume Dumas

Scientific Machine Learning (SciML) is a burgeoning field that synergistically combines domain-aware and interpretable models with agnostic machine learning techniques.

Representation Learning

Maximum State Entropy Exploration using Predecessor and Successor Representations

no code implementations26 Jun 2023 Arnav Kumar Jain, Lucas Lehnert, Irina Rish, Glen Berseth

Animals have a developed ability to explore that aids them in important tasks such as locating food, exploring for shelter, and finding misplaced items.

Efficient Exploration

Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok

no code implementations23 Jun 2023 Pascal Jr. Tikeng Notsawo, Hattie Zhou, Mohammad Pezeshki, Irina Rish, Guillaume Dumas

In essence, by studying the learning curve of the first few epochs, we show that one can predict whether grokking will occur later on.


Towards ethical multimodal systems

no code implementations26 Apr 2023 Alexis Roger, Esma Aïmeur, Irina Rish

We perform the evaluation of these models in two steps: we first discus the creation of a multimodal ethical database and then use this database to construct morality-evaluating algorithms.

A Survey on Compositional Generalization in Applications

no code implementations2 Feb 2023 Baihan Lin, Djallel Bouneffouf, Irina Rish

The field of compositional generalization is currently experiencing a renaissance in AI, as novel problem settings and algorithms motivated by various practical applications are being introduced, building on top of the classical compositional generalization problem.

Knowledge Distillation for Federated Learning: a Practical Guide

no code implementations9 Nov 2022 Alessio Mora, Irene Tenison, Paolo Bellavista, Irina Rish

Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data.

Federated Learning Knowledge Distillation

Broken Neural Scaling Laws

1 code implementation26 Oct 2022 Ethan Caballero, Kshitij Gupta, Irina Rish, David Krueger

Moreover, this functional form accurately models and extrapolates scaling behavior that other functional forms are incapable of expressing such as the non-monotonic transitions present in the scaling behavior of phenomena such as double descent and the delayed, sharp inflection points present in the scaling behavior of tasks such as arithmetic.

Adversarial Robustness Continual Learning +7

Aligning MAGMA by Few-Shot Learning and Finetuning

no code implementations18 Oct 2022 Jean-Charles Layoun, Alexis Roger, Irina Rish

The goal of vision-language modeling is to allow models to tie language understanding with visual inputs.

Few-Shot Learning Image Captioning +3

Cognitive Models as Simulators: The Case of Moral Decision-Making

no code implementations8 Oct 2022 Ardavan S. Nobandegani, Thomas R. Shultz, Irina Rish

In this work, we substantiate the idea of $\textit{cognitive models as simulators}$, which is to have AI systems interact with, and collect feedback from, cognitive models instead of humans, thereby making their training process both less costly and faster.

Decision Making Fairness +1

Towards Out-of-Distribution Adversarial Robustness

1 code implementation6 Oct 2022 Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas, Irina Rish, David Krueger, Pouya Bashivan

Compared to existing methods, we obtain similar or superior worst-case adversarial robustness on attacks seen during training.

Adversarial Robustness

Challenging Common Assumptions about Catastrophic Forgetting

no code implementations10 Jul 2022 Timothée Lesort, Oleksiy Ostapenko, Diganta Misra, Md Rifat Arefin, Pau Rodríguez, Laurent Charlin, Irina Rish

In this paper, we study the progressive knowledge accumulation (KA) in DNNs trained with gradient-based algorithms in long sequences of tasks with data re-occurrence.

Continual Learning Memorization

Continual Learning with Foundation Models: An Empirical Study of Latent Replay

1 code implementation30 Apr 2022 Oleksiy Ostapenko, Timothee Lesort, Pau Rodríguez, Md Rifat Arefin, Arthur Douillard, Irina Rish, Laurent Charlin

Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios.

Benchmarking Continual Learning

APP: Anytime Progressive Pruning

1 code implementation4 Apr 2022 Diganta Misra, Bharat Runwal, Tianlong Chen, Zhangyang Wang, Irina Rish

With the latest advances in deep learning, there has been a lot of focus on the online learning paradigm due to its relevance in practical settings.

Network Pruning Sparse Learning

Towards Scaling Difference Target Propagation by Learning Backprop Targets

1 code implementation31 Jan 2022 Maxence Ernoult, Fabrice Normandin, Abhinav Moudgil, Sean Spinney, Eugene Belilovsky, Irina Rish, Blake Richards, Yoshua Bengio

As such, it is important to explore learning algorithms that come with strong theoretical guarantees and can match the performance of backpropagation (BP) on complex tasks.

Gradient Masked Averaging for Federated Learning

no code implementations28 Jan 2022 Irene Tenison, Sai Aravind Sreeramadas, Vaikkunth Mugunthan, Edouard Oyallon, Eugene Belilovsky, Irina Rish

Standard federated learning algorithms involve averaging of model parameters or gradient updates to approximate the global model at the server.

Federated Learning

Generative Models of Brain Dynamics -- A review

no code implementations22 Dec 2021 Mahta Ramezanian Panahi, Germán Abrevaya, Jean-Christophe Gagnon-Audet, Vikram Voleti, Irina Rish, Guillaume Dumas

The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-twentieth century.

Compositional Attention: Disentangling Search and Retrieval

3 code implementations ICLR 2022 Sarthak Mittal, Sharath Chandra Raparthy, Irina Rish, Yoshua Bengio, Guillaume Lajoie

Through our qualitative analysis, we demonstrate that Compositional Attention leads to dynamic specialization based on the type of retrieval needed.


Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers

no code implementations13 Oct 2021 Gabriele Prato, Simon Guiroy, Ethan Caballero, Irina Rish, Sarath Chandar

Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning, particularly in the light of recent breakthroughs achieved by large-scale pre-trained models such as GPT-3, CLIP and DALL-e.

Few-Shot Learning Image Classification

Exploring the Optimality of Tight-Frame Scattering Networks

no code implementations29 Sep 2021 Shanel Gauthier, Benjamin Thérien, Laurent Alsène-Racicot, Muawiz Sajjad Chaudhary, Irina Rish, Eugene Belilovsky, Michael Eickenberg, Guy Wolf

The wavelet filters used in the scattering transform are typically selected to create a tight frame via a parameterized mother wavelet.

Approximate Bayesian Optimisation for Neural Networks

no code implementations27 Aug 2021 Nadhir Hassen, Irina Rish

A body of work has been done to automate machine learning algorithm to highlight the importance of model choice.

Bayesian Optimisation Density Ratio Estimation +1

SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization

2 code implementations4 Jun 2021 Soroosh Shahtalebi, Jean-Christophe Gagnon-Audet, Touraj Laleh, Mojtaba Faramarzi, Kartik Ahuja, Irina Rish

A major bottleneck in the real-world applications of machine learning models is their failure in generalizing to unseen domains whose data distribution is not i. i. d to the training domains.

Domain Generalization

Continual Learning in Deep Networks: an Analysis of the Last Layer

no code implementations3 Jun 2021 Timothée Lesort, Thomas George, Irina Rish

Our analysis and results shed light on the dynamics of the output layer in continual learning scenarios and suggest a way of selecting the best type of output layer for a given scenario.

Continual Learning

Gradient Masked Federated Optimization

no code implementations21 Apr 2021 Irene Tenison, Sreya Francis, Irina Rish

Federated Averaging (FedAVG) has become the most popular federated learning algorithm due to its simplicity and low communication overhead.

Federated Learning

Towards Causal Federated Learning For Enhanced Robustness and Privacy

no code implementations14 Apr 2021 Sreya Francis, Irene Tenison, Irina Rish

In this paper, we propose an approach for learning invariant (causal) features common to all participating clients in a federated learning setup and analyze empirically how it enhances the Out of Distribution (OOD) accuracy as well as the privacy of the final learned model.

Federated Learning Privacy Preserving

Understanding Continual Learning Settings with Data Distribution Drift Analysis

no code implementations4 Apr 2021 Timothée Lesort, Massimo Caccia, Irina Rish

In this paper, we aim to identify and categorize different types of context drifts and potential assumptions about them, to better characterize various continual-learning scenarios.

BIG-bench Machine Learning Continual Learning

Towards Continual Reinforcement Learning: A Review and Perspectives

no code implementations25 Dec 2020 Khimya Khetarpal, Matthew Riemer, Irina Rish, Doina Precup

In this article, we aim to provide a literature review of different formulations and approaches to continual reinforcement learning (RL), also known as lifelong or non-stationary RL.

Continual Learning reinforcement-learning +1

Predicting Infectiousness for Proactive Contact Tracing

1 code implementation ICLR 2021 Yoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Muller, Meng Qu, Victor Schmidt, Pierre-Luc St-Charles, Hannah Alsdurf, Olexa Bilanuik, David Buckeridge, Gáetan Marceau Caron, Pierre-Luc Carrier, Joumana Ghosn, Satya Ortiz-Gagne, Chris Pal, Irina Rish, Bernhard Schölkopf, Abhinav Sharma, Jian Tang, Andrew Williams

Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT).

Double-Linear Thompson Sampling for Context-Attentive Bandits

no code implementations15 Oct 2020 Djallel Bouneffouf, Raphaël Féraud, Sohini Upadhyay, Yasaman Khazaeni, Irina Rish

In this paper, we analyze and extend an online learning framework known as Context-Attentive Bandit, motivated by various practical applications, from medical diagnosis to dialog systems, where due to observation costs only a small subset of a potentially large number of context variables can be observed at each iteration;however, the agent has a freedom to choose which variables to observe.

Medical Diagnosis Thompson Sampling

Chaotic Continual Learning

no code implementations ICML Workshop LifelongML 2020 Touraj Laleh, Mojtaba Faramarzi, Irina Rish, Sarath Chandar

Most proposed approaches for this issue try to compensate for the effects of parameter updates in the batch incremental setup in which the training model visits a lot of samples for several epochs.

Continual Learning

Adversarial Feature Desensitization

1 code implementation NeurIPS 2021 Pouya Bashivan, Reza Bayat, Adam Ibrahim, Kartik Ahuja, Mojtaba Faramarzi, Touraj Laleh, Blake Aaron Richards, Irina Rish

Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs.

Adversarial Robustness Domain Adaptation +1

Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL

1 code implementation10 May 2020 Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen, Irina Rish

Artificial behavioral agents are often evaluated based on their consistent behaviors and performance to take sequential actions in an environment to maximize some notion of cumulative reward.

Decision Making Multi-Armed Bandits +1

Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation

1 code implementation31 Mar 2020 Victor Schmidt, Makesh Narsimhan Sreedhar, Mostafa ElAraby, Irina Rish

Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling.

Colorization Continual Learning +3

Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders

no code implementations NeurIPS Workshop Neuro_AI 2019 Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen, Irina Rish

Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for a reinforcement learning problem, which extends the standard Q-learning approach to incorporate a two-stream framework of reward processing with biases biologically associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain.

Decision Making Q-Learning +3

A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry

1 code implementation21 Jun 2019 Baihan Lin, Guillermo Cecchi, Djallel Bouneffouf, Jenna Reinen, Irina Rish

Drawing an inspiration from behavioral studies of human decision making, we propose here a more general and flexible parametric framework for reinforcement learning that extends standard Q-learning to a two-stream model for processing positive and negative rewards, and allows to incorporate a wide range of reward-processing biases -- an important component of human decision making which can help us better understand a wide spectrum of multi-agent interactions in complex real-world socioeconomic systems, as well as various neuropsychiatric conditions associated with disruptions in normal reward processing.

Decision Making Q-Learning +2

Continual Learning with Self-Organizing Maps

no code implementations19 Apr 2019 Pouya Bashivan, Martin Schrimpf, Robert Ajemian, Irina Rish, Matthew Riemer, Yuhai Tu

Most previous approaches to this problem rely on memory replay buffers which store samples from previously learned tasks, and use them to regularize the learning on new ones.

Continual Learning

A Survey on Practical Applications of Multi-Armed and Contextual Bandits

no code implementations2 Apr 2019 Djallel Bouneffouf, Irina Rish

In recent years, multi-armed bandit (MAB) framework has attracted a lot of attention in various applications, from recommender systems and information retrieval to healthcare and finance, due to its stellar performance combined with certain attractive properties, such as learning from less feedback.

Information Retrieval Multi-Armed Bandits +2

Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference

2 code implementations ICLR 2019 Matthew Riemer, Ignacio Cases, Robert Ajemian, Miao Liu, Irina Rish, Yuhai Tu, Gerald Tesauro

In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples.

Continual Learning Meta-Learning

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables

1 code implementation24 Jun 2018 Anna Choromanska, Benjamin Cowen, Sadhana Kumaravel, Ronny Luss, Mattia Rigotti, Irina Rish, Brian Kingsbury, Paolo DiAchille, Viatcheslav Gurev, Ravi Tejwani, Djallel Bouneffouf

Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function.

Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach

no code implementations26 Apr 2018 Sahil Garg, Irina Rish, Guillermo Cecchi, Palash Goyal, Sarik Ghazarian, Shuyang Gao, Greg Ver Steeg, Aram Galstyan

We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses.

Dialogue Generation Model Selection

Contextual Bandit with Adaptive Feature Extraction

1 code implementation3 Feb 2018 Baihan Lin, Djallel Bouneffouf, Guillermo Cecchi, Irina Rish

Our experiments on a variety of datasets, and both in stationary and non-stationary environments of several kinds demonstrate clear advantages of the proposed adaptive representation learning over the standard contextual bandit based on "raw" input contexts.

Clustering Decision Making +2

Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks

no code implementations1 Dec 2017 Jumana Dakka, Pouya Bashivan, Mina Gheiratmand, Irina Rish, Shantenu Jha, Russell Greiner

Smart systems that can accurately diagnose patients with mental disorders and identify effective treatments based on brain functional imaging data are of great applicability and are gaining much attention.

Kernelized Hashcode Representations for Relation Extraction

1 code implementation10 Nov 2017 Sahil Garg, Aram Galstyan, Greg Ver Steeg, Irina Rish, Guillermo Cecchi, Shuyang Gao

Here we propose to use random subspaces of KLSH codes for efficiently constructing an explicit representation of NLP structures suitable for general classification methods.

General Classification Relation Extraction

Bandit Models of Human Behavior: Reward Processing in Mental Disorders

no code implementations7 Jun 2017 Djallel Bouneffouf, Irina Rish, Guillermo A. Cecchi

Drawing an inspiration from behavioral studies of human decision making, we propose here a general parametric framework for multi-armed bandit problem, which extends the standard Thompson Sampling approach to incorporate reward processing biases associated with several neurological and psychiatric conditions, including Parkinson's and Alzheimer's diseases, attention-deficit/hyperactivity disorder (ADHD), addiction, and chronic pain.

Decision Making Thompson Sampling

Context Attentive Bandits: Contextual Bandit with Restricted Context

no code implementations10 May 2017 Djallel Bouneffouf, Irina Rish, Guillermo A. Cecchi, Raphael Feraud

We consider a novel formulation of the multi-armed bandit model, which we call the contextual bandit with restricted context, where only a limited number of features can be accessed by the learner at every iteration.

Recommendation Systems Thompson Sampling

Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World

1 code implementation22 Jan 2017 Sahil Garg, Irina Rish, Guillermo Cecchi, Aurelie Lozano

In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture.

Dictionary Learning Hippocampus +2

Mental State Recognition via Wearable EEG

no code implementations2 Feb 2016 Pouya Bashivan, Irina Rish, Steve Heisig

The increasing quality and affordability of consumer electroencephalogram (EEG) headsets make them attractive for situations where medical grade devices are impractical.

EEG Electroencephalogram (EEG)

Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks

11 code implementations19 Nov 2015 Pouya Bashivan, Irina Rish, Mohammed Yeasin, Noel Codella

One of the challenges in modeling cognitive events from electroencephalogram (EEG) data is finding representations that are invariant to inter- and intra-subject differences, as well as to inherent noise associated with such data.

EEG Electroencephalogram (EEG) +4

MINT: Mutual Information based Transductive Feature Selection for Genetic Trait Prediction

no code implementations7 Oct 2013 Dan He, Irina Rish, David Haws, Simon Teyssedre, Zivan Karaman, Laxmi Parida

Whole genome prediction of complex phenotypic traits using high-density genotyping arrays has attracted a great deal of attention, as it is relevant to the fields of plant and animal breeding and genetic epidemiology.

Epidemiology feature selection

Discriminative Network Models of Schizophrenia

no code implementations NeurIPS 2009 Irina Rish, Benjamin Thyreau, Bertrand Thirion, Marion Plaze, Marie-Laure Paillere-Martinot, Catherine Martelli, Jean-Luc Martinot, Jean-Baptiste Poline, Guillermo A. Cecchi

Schizophrenia is a complex psychiatric disorder that has eluded a characterization in terms of local abnormalities of brain activity, and is hypothesized to affect the collective, ``emergent working of the brain.

Cannot find the paper you are looking for? You can Submit a new open access paper.