Alessandro Achille

research

∙ 08/23/2023

Critical Learning Periods Emerge Even in Deep Linear Networks

Critical learning periods are periods early in development where tempora...

0 Michael Kleinman, et al. ∙

research

∙ 08/02/2023

Training Data Protection with Compositional Diffusion Models

We introduce Compartmentalized Diffusion Models (CDM), a method to train...

0 Aditya Golatkar, et al. ∙

research

∙ 06/06/2023

Towards Visual Foundational Models of Physical Scenes

We describe a first step towards learning general-purpose visual represe...

0 Chethan Parameshwara, et al. ∙

research

∙ 06/01/2023

Prompt Algebra for Task Composition

We investigate whether prompts learned independently for different tasks...

0 Pramuditha Perera, et al. ∙

research

∙ 04/25/2023

SAFE: Machine Unlearning With Shard Graphs

We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt l...

0 Yonatan Dukler, et al. ∙

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 ...

0 Marco Fumero, et al. ∙

research

∙ 04/07/2023

AI Model Disgorgement: Methods and Choices

Responsible use of data is an indispensable part of any machine learning...

0 Alessandro Achille, et al. ∙

research

∙ 03/25/2023

Train/Test-Time Adaptation with Retrieval

We introduce Train/Test-Time Adaptation with Retrieval (T^3AR), a method...

0 Luca Zancato, et al. ∙

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...

0 Yonatan Dukler, et al. ∙

research

∙ 03/03/2023

Spacetime-Efficient Low-Depth Quantum State Preparation with Applications

We propose a novel deterministic method for preparing arbitrary quantum ...

0 Kaiwen Gui, et al. ∙

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 ...

0 Achin Jain, et al. ∙

research

∙ 02/28/2023

Linear Spaces of Meanings: the Compositional Language of VLMs

We investigate compositional structures in vector data embeddings from p...

0 Matthew Trager, et al. ∙

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 ...

0 Benjamin Bowman, et al. ∙

research

∙ 11/23/2022

Integral Continual Learning Along the Tangent Vector Field of Tasks

We propose a continual learning method which incorporates information fr...

0 Tian Yu Liu, et al. ∙

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...

0 Michael Kleinman, et al. ∙

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...

8 Alessandro Achille, et al. ∙

research

∙ 07/01/2022

On Leave-One-Out Conditional Mutual Information For Generalization

We derive information theoretic generalization bounds for supervised lea...

8 Mohamad Rida Rammal, et al. ∙

research

∙ 05/24/2022

Gacs-Korner Common Information Variational Autoencoder

We propose a notion of common information that allows one to quantify an...

7 Michael Kleinman, et al. ∙

research

∙ 03/30/2022

Task Adaptive Parameter Sharing for Multi-Task Learning

Adapting pre-trained models with broad capabilities has become standard ...

1 Matthew Wallingford, et al. ∙

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...

0 Simone Bombari, et al. ∙

research

∙ 03/22/2022

Mixed Differential Privacy in Computer Vision

We introduce AdaMix, an adaptive differentially private algorithm for tr...

18 Aditya Golatkar, et al. ∙

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...

9 Yonatan Dukler, et al. ∙

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...

21 Aditya Deshpande, et al. ∙

research

∙ 01/17/2021

Estimating informativeness of samples with Smooth Unique Information

We define a notion of information that an individual sample provides to ...

6 Hrayr Harutyunyan, et al. ∙

research

∙ 01/14/2021

Structured Prediction as Translation between Augmented Natural Languages

We propose a new framework, Translation between Augmented Natural Langua...

7 Giovanni Paolini, et al. ∙

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...

16 Aditya Golatkar, et al. ∙

research

∙ 12/21/2020

LQF: Linear Quadratic Fine-Tuning

Classifiers that are linear in their parameters, and trained by optimizi...

8 Alessandro Achille, et al. ∙

research

∙ 10/06/2020

Usable Information and Evolution of Optimal Representations During Training

We introduce a notion of usable information contained in the representat...

0 Michael Kleinman, et al. ∙

research

∙ 08/28/2020

Predicting Training Time Without Training

We tackle the problem of predicting the number of optimization steps tha...

21 Luca Zancato, et al. ∙

research

∙ 07/22/2020

Adversarial Training Reduces Information and Improves Transferability

Recent results show that features of adversarially trained networks for ...

0 Matteo Terzi, et al. ∙

research

∙ 06/25/2020

Layout Generation and Completion with Self-attention

We address the problem of layout generation for diverse domains such as ...

5 Kamal Gupta, et al. ∙

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 ...

1 Aditya Golatkar, et al. ∙

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 ...

15 Joël Seytre, et al. ∙

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...

20 Aditya Golatkar, et al. ∙

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...

16 Aditya Golatkar, et al. ∙

research

∙ 08/02/2019

Toward Understanding Catastrophic Forgetting in Continual Learning

We study the relationship between catastrophic forgetting and properties...

8 Cuong V. Nguyen, et al. ∙

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...

0 Aditya Golatkar, et 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...

0 Alessandro Achille, et al. ∙

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 ...

26 Alessandro Achille, et al. ∙

research

∙ 02/10/2019

Task2Vec: Task Embedding for Meta-Learning

We introduce a method to provide vectorial representations of visual cla...

10 Alessandro Achille, et al. ∙

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 ...

0 Alessandro Achille, et al. ∙

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 ...

0 Alessandro Achille, et al. ∙

research

∙ 11/24/2017

Critical Learning Periods in Deep Neural Networks

Critical periods are phases in the early development of humans and anima...

0 Alessandro Achille, et al. ∙

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 ...

0 Alessandro Achille, et al. ∙

research

∙ 06/05/2017

Emergence of Invariance and Disentangling in Deep Representations

Using established principles from Information Theory and Statistics, we ...

0 Alessandro Achille, et al. ∙

research

∙ 11/04/2016

Information Dropout: Learning Optimal Representations Through Noisy Computation

The cross-entropy loss commonly used in deep learning is closely related...

0 Alessandro Achille, et al. ∙

Alessandro Achille

Featured Co-authors