research
∙
08/23/2023
Critical Learning Periods Emerge Even in Deep Linear Networks
Critical learning periods are periods early in development where tempora...
share
research
∙
08/02/2023
Training Data Protection with Compositional Diffusion Models
We introduce Compartmentalized Diffusion Models (CDM), a method to train...
research
∙
06/06/2023
Towards Visual Foundational Models of Physical Scenes
We describe a first step towards learning general-purpose visual represe...
research
∙
06/01/2023
Prompt Algebra for Task Composition
We investigate whether prompts learned independently for different tasks...
research
∙
04/25/2023
SAFE: Machine Unlearning With Shard Graphs
We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt l...
research
∙
04/17/2023
Leveraging sparse and shared feature activations for disentangled representation learning
Recovering the latent factors of variation of high dimensional data has ...
research
∙
04/07/2023
AI Model Disgorgement: Methods and Choices
Responsible use of data is an indispensable part of any machine learning...
research
∙
03/25/2023
Train/Test-Time Adaptation with Retrieval
We introduce Train/Test-Time Adaptation with Retrieval (T^3AR), a method...
research
∙
03/07/2023
Introspective Cross-Attention Probing for Lightweight Transfer of Pre-trained Models
We propose InCA, a lightweight method for transfer learning that cross-a...
research
∙
03/03/2023
Spacetime-Efficient Low-Depth Quantum State Preparation with Applications
We propose a novel deterministic method for preparing arbitrary quantum ...
research
∙
03/02/2023
A Meta-Learning Approach to Predicting Performance and Data Requirements
We propose an approach to estimate the number of samples required for a ...
research
∙
02/28/2023
Linear Spaces of Meanings: the Compositional Language of VLMs
We investigate compositional structures in vector data embeddings from p...
research
∙
02/15/2023
À-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting
We introduce À-la-carte Prompt Tuning (APT), a transformer-based scheme ...
research
∙
11/23/2022
Integral Continual Learning Along the Tangent Vector Field of Tasks
We propose a continual learning method which incorporates information fr...
research
∙
10/06/2022
Critical Learning Periods for Multisensory Integration in Deep Networks
We show that the ability of a neural network to integrate information fr...
research
∙
07/25/2022
On the Learnability of Physical Concepts: Can a Neural Network Understand What's Real?
We revisit the classic signal-to-symbol barrier in light of the remarkab...
research
∙
07/01/2022
On Leave-One-Out Conditional Mutual Information For Generalization
We derive information theoretic generalization bounds for supervised lea...
research
∙
05/24/2022
Gacs-Korner Common Information Variational Autoencoder
We propose a notion of common information that allows one to quantify an...
research
∙
03/30/2022
Task Adaptive Parameter Sharing for Multi-Task Learning
Adapting pre-trained models with broad capabilities has become standard ...
research
∙
03/30/2022
Towards Differential Relational Privacy and its use in Question Answering
Memorization of the relation between entities in a dataset can lead to p...
research
∙
03/22/2022
Mixed Differential Privacy in Computer Vision
We introduce AdaMix, an adaptive differentially private algorithm for tr...
research
∙
11/18/2021
DIVA: Dataset Derivative of a Learning Task
We present a method to compute the derivative of a learning task with re...
research
∙
01/29/2021
A linearized framework and a new benchmark for model selection for fine-tuning
Fine-tuning from a collection of models pre-trained on different domains...
research
∙
01/17/2021
Estimating informativeness of samples with Smooth Unique Information
We define a notion of information that an individual sample provides to ...
research
∙
01/14/2021
Structured Prediction as Translation between Augmented Natural Languages
We propose a new framework, Translation between Augmented Natural Langua...
research
∙
12/24/2020
Mixed-Privacy Forgetting in Deep Networks
We show that the influence of a subset of the training samples can be re...
research
∙
12/21/2020
LQF: Linear Quadratic Fine-Tuning
Classifiers that are linear in their parameters, and trained by optimizi...
research
∙
10/06/2020
Usable Information and Evolution of Optimal Representations During Training
We introduce a notion of usable information contained in the representat...
research
∙
08/28/2020
Predicting Training Time Without Training
We tackle the problem of predicting the number of optimization steps tha...
research
∙
07/22/2020
Adversarial Training Reduces Information and Improves Transferability
Recent results show that features of adversarially trained networks for ...
research
∙
06/25/2020
Layout Generation and Completion with Self-attention
We address the problem of layout generation for diverse domains such as ...
research
∙
03/05/2020
Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations
We describe a procedure for removing dependency on a cohort of training ...
research
∙
12/19/2019
TextTubes for Detecting Curved Text in the Wild
We present a detector for curved text in natural images. We model scene ...
research
∙
11/12/2019
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Neural Networks
We explore the problem of selectively forgetting a particular set of dat...
research
∙
11/12/2019
Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
We explore the problem of selectively forgetting a particular set of dat...
research
∙
08/02/2019
Toward Understanding Catastrophic Forgetting in Continual Learning
We study the relationship between catastrophic forgetting and properties...
research
∙
05/30/2019
Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence
Regularization is typically understood as improving generalization by al...
research
∙
05/29/2019
Where is the Information in a Deep Neural Network?
Whatever information a Deep Neural Network has gleaned from past data is...
research
∙
04/05/2019
The Information Complexity of Learning Tasks, their Structure and their Distance
We introduce an asymmetric distance in the space of learning tasks, and ...
research
∙
02/10/2019
Task2Vec: Task Embedding for Meta-Learning
We introduce a method to provide vectorial representations of visual cla...
research
∙
10/04/2018
The Dynamics of Differential Learning I: Information-Dynamics and Task Reachability
We study the topology of the space of learning tasks, which is critical ...
research
∙
08/20/2018
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
Intelligent behaviour in the real-world requires the ability to acquire ...
research
∙
11/24/2017
Critical Learning Periods in Deep Neural Networks
Critical periods are phases in the early development of humans and anima...
research
∙
11/09/2017
A Separation Principle for Control in the Age of Deep Learning
We review the problem of defining and inferring a "state" for a control ...
research
∙
06/05/2017
Emergence of Invariance and Disentangling in Deep Representations
Using established principles from Information Theory and Statistics, we ...
research
∙
11/04/2016