Search Results for author:
Found 82 papers, 38 papers with code
Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training
Our results show that the infinite learning rate schedule remains effective at scale, surpassing repeated cosine decay for both MAE pre-training and zero-shot LM benchmarks.
Artificial Neural Networks for Magnetoencephalography: A review of an emerging field
Second, we report on work that has used ANNs as putative models of information processing in the human brain.
Robin: a Suite of Multi-Scale Vision-Language Models and the CHIRP Evaluation Benchmark
The proliferation of Vision-Language Models (VLMs) in the past several years calls for rigorous and comprehensive evaluation methods and benchmarks.
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret.
RedPajama: an Open Dataset for Training Large Language Models
In addition, we release RedPajama-V2, a massive web-only dataset consisting of raw, unfiltered text data together with quality signals and metadata.
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment.
GitChameleon: Unmasking the Version-Switching Capabilities of Code Generation Models
The rapid evolution of software libraries presents a significant challenge for code generation models, which must adapt to frequent version updates while maintaining compatibility with previous versions.
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
To address this, we propose Sequential Variance-Covariance Regularization (Seq-VCR), which enhances the entropy of intermediate representations and prevents collapse.
Context is Key: A Benchmark for Forecasting with Essential Textual Information
To address this, we introduce "Context is Key" (CiK), a time series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities.
VFA: Vision Frequency Analysis of Foundation Models and Human
Machine learning models often struggle with distribution shifts in real-world scenarios, whereas humans exhibit robust adaptation.
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
Rapid advancements in GPU computational power has outpaced memory capacity and bandwidth growth, creating bottlenecks in Large Language Model (LLM) inference.
Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
Understanding the mechanisms behind decisions taken by large foundation models in sequential decision making tasks is critical to ensuring that such systems operate transparently and safely.
Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
Vision-Language Models (VLMs) have witnessed a surge in both research and real-world applications.
Lost in Translation: The Algorithmic Gap Between LMs and the Brain
Language Models (LMs) have achieved impressive performance on various linguistic tasks, but their relationship to human language processing in the brain remains unclear.
$μ$LO: Compute-Efficient Meta-Generalization of Learned Optimizers
We extend $\mu$P theory to learned optimizers, treating the meta-training problem as finding the learned optimizer under $\mu$P.
Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI
In addition to the data efficiency gained from direct sampling, we propose an algorithm that offers a significant reduction in sample complexity for estimating the divergence of the data distribution with respect to the marginal distribution.
Simple and Scalable Strategies to Continually Pre-train Large Language Models
In this work, we show that a simple and scalable combination of learning rate (LR) re-warming, LR re-decaying, and replay of previous data is sufficient to match the performance of fully re-training from scratch on all available data, as measured by the final loss and the average score on several language model (LM) evaluation benchmarks.
Unsupervised Concept Discovery Mitigates Spurious Correlations
Models prone to spurious correlations in training data often produce brittle predictions and introduce unintended biases.
Towards Machines that Trust: AI Agents Learn to Trust in the Trust Game
Widely considered a cornerstone of human morality, trust shapes many aspects of human social interactions.
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Over the past years, foundation models have caused a paradigm shift in machine learning due to their unprecedented capabilities for zero-shot and few-shot generalization.
LORD: Low Rank Decomposition Of Monolingual Code LLMs For One-Shot Compression
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.
Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning
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?
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.
Effective Latent Differential Equation Models via Attention and Multiple Shooting
Scientific Machine Learning (SciML) is a burgeoning field that synergistically combines domain-aware and interpretable models with agnostic machine learning techniques.
Predicting Grokking Long Before it Happens: A look into the loss landscape of models which grok
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
Generative AI systems (ChatGPT, DALL-E, etc) are expanding into multiple areas of our lives, from art Rombach et al. [2021] to mental health Rob Morris and Kareem Kouddous [2022]; their rapidly growing societal impact opens new opportunities, but also raises ethical concerns.
A Survey on Compositional Generalization in Applications
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
Federated Learning (FL) enables the training of Deep Learning models without centrally collecting possibly sensitive raw data.
Broken Neural Scaling Laws
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.
Aligning MAGMA by Few-Shot Learning and Finetuning
The goal of vision-language modeling is to allow models to tie language understanding with visual inputs.
Cognitive Models as Simulators: The Case of Moral Decision-Making
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.
Towards Out-of-Distribution Adversarial Robustness
Compared to existing methods, we obtain similar or superior worst-case adversarial robustness on attacks seen during training.
Challenging Common Assumptions about Catastrophic Forgetting
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 with Foundation Models: An Empirical Study of Latent Replay
Motivated by this, we study the efficacy of pre-trained vision models as a foundation for downstream continual learning (CL) scenarios.
APP: Anytime Progressive Pruning
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.
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
We revise the existing OOD generalization algorithms for time series tasks and evaluate them using our systematic framework.
Towards Scaling Difference Target Propagation by Learning Backprop Targets
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
A major challenge in federated learning is the heterogeneity of data across client, which can degrade the performance of standard FL algorithms.
Generative Models of Brain Dynamics -- A review
The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-twentieth century.
Continual Learning In Environments With Polynomial Mixing Times
The mixing time of the Markov chain induced by a policy limits performance in real-world continual learning scenarios.
Compositional Attention: Disentangling Search and Retrieval
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
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.
Exploring the Optimality of Tight-Frame Scattering Networks
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
A body of work has been done to automate machine learning algorithm to highlight the importance of model choice.
Sequoia: A Software Framework to Unify Continual Learning Research
We propose a taxonomy of settings, where each setting is described as a set of assumptions.
Parametric Scattering Networks
The wavelet scattering transform creates geometric invariants and deformation stability.
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization
To answer these questions, we revisit the fundamental assumptions in linear regression tasks, where invariance-based approaches were shown to provably generalize OOD.
SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization
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.
Continual Learning in Deep Networks: an Analysis of the Last Layer
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.
Gradient Masked Federated Optimization
Federated Averaging (FedAVG) has become the most popular federated learning algorithm due to its simplicity and low communication overhead.
Towards Causal Federated Learning For Enhanced Robustness and Privacy
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.
Understanding Continual Learning Settings with Data Distribution Drift Analysis
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.
Towards Continual Reinforcement Learning: A Review and Perspectives
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.
Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning
The main challenge is that the agent must not forget previous tasks and also adapt to novel tasks in the stream.
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution.
Predicting Infectiousness for Proactive Contact Tracing
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
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.
Chaotic Continual Learning
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.
Adversarial Feature Desensitization
Our method, called Adversarial Feature Desensitization (AFD), aims at learning features that are invariant towards adversarial perturbations of the inputs.
COVI White Paper
Manual contact tracing of Covid-19 cases has significant challenges that limit the ability of public health authorities to minimize community infections.
Unified Models of Human Behavioral Agents in Bandits, Contextual Bandits and RL
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.
Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation
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.
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario.
Reinforcement Learning Models of Human Behavior: Reward Processing in Mental Disorders
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.
A Story of Two Streams: Reinforcement Learning Models from Human Behavior and Neuropsychiatry
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.
Continual Learning with Self-Organizing Maps
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.
A Survey on Practical Applications of Multi-Armed and Contextual Bandits
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.
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
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.
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function.
Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM
Many real-world data sets, especially in biology, are produced by complex nonlinear dynamical systems.
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
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.
Contextual Bandit with Adaptive Feature Extraction
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.
Learning Neural Markers of Schizophrenia Disorder Using Recurrent Neural Networks
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
Here we propose to use random subspaces of KLSH codes for efficiently constructing an explicit representation of NLP structures suitable for general classification methods.
Bandit Models of Human Behavior: Reward Processing in Mental Disorders
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.
Context Attentive Bandits: Contextual Bandit with Restricted Context
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.
Neurogenesis-Inspired Dictionary Learning: Online Model Adaption in a Changing World
In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture.
NIPS 2016 Workshop on Representation Learning in Artificial and Biological Neural Networks (MLINI 2016)
The goal is to understand the brain by trying to find the function that expresses the activity of brain areas in terms of different properties of the stimulus.
Mental State Recognition via Wearable EEG
The increasing quality and affordability of consumer electroencephalogram (EEG) headsets make them attractive for situations where medical grade devices are impractical.
Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
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.
MINT: Mutual Information based Transductive Feature Selection for Genetic Trait Prediction
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.
Discriminative Network Models of Schizophrenia
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.
