Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Alessandro Achille

A linearized framework and a new benchmark for model selection for fine-tuning


Jan 29, 2021
Aditya Deshpande, Alessandro Achille, Avinash Ravichandran, Hao Li, Luca Zancato, Charless Fowlkes, Rahul Bhotika, Stefano Soatto, Pietro Perona

* 14 pages 

  Access Paper or Ask Questions

Structured Prediction as Translation between Augmented Natural Languages


Jan 28, 2021
Giovanni Paolini, Ben Athiwaratkun, Jason Krone, Jie Ma, Alessandro Achille, Rishita Anubhai, Cicero Nogueira dos Santos, Bing Xiang, Stefano Soatto


  Access Paper or Ask Questions

Estimating informativeness of samples with Smooth Unique Information


Jan 17, 2021
Hrayr Harutyunyan, Alessandro Achille, Giovanni Paolini, Orchid Majumder, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

* ICLR 2021, 22 pages 

  Access Paper or Ask Questions

Mixed-Privacy Forgetting in Deep Networks


Dec 24, 2020
Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, Stefano Soatto


  Access Paper or Ask Questions

LQF: Linear Quadratic Fine-Tuning


Dec 21, 2020
Alessandro Achille, Aditya Golatkar, Avinash Ravichandran, Marzia Polito, Stefano Soatto


  Access Paper or Ask Questions

Usable Information and Evolution of Optimal Representations During Training


Oct 06, 2020
Michael Kleinman, Daksh Idnani, Alessandro Achille, Jonathan C. Kao


  Access Paper or Ask Questions

Predicting Training Time Without Training


Aug 28, 2020
Luca Zancato, Alessandro Achille, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto


  Access Paper or Ask Questions

Adversarial Training Reduces Information and Improves Transferability


Aug 21, 2020
Matteo Terzi, Alessandro Achille, Marco Maggipinto, Gian Antonio Susto


  Access Paper or Ask Questions

Layout Generation and Completion with Self-attention


Jun 25, 2020
Kamal Gupta, Alessandro Achille, Justin Lazarow, Larry Davis, Vijay Mahadevan, Abhinav Shrivastava


  Access Paper or Ask Questions

Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations


Mar 16, 2020
Aditya Golatkar, Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions

TextTubes for Detecting Curved Text in the Wild


Dec 19, 2019
Joël Seytre, Jon Wu, Alessandro Achille


  Access Paper or Ask Questions

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks


Nov 25, 2019
Aditya Golatkar, Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions

Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Neural Networks


Nov 12, 2019
Aditya Golatkar, Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions

Toward Understanding Catastrophic Forgetting in Continual Learning


Aug 02, 2019
Cuong V. Nguyen, Alessandro Achille, Michael Lam, Tal Hassner, Vijay Mahadevan, Stefano Soatto


  Access Paper or Ask Questions

Where is the Information in a Deep Neural Network?


Jun 04, 2019
Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions

Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence


May 30, 2019
Aditya Golatkar, Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions

The Information Complexity of Learning Tasks, their Structure and their Distance


Apr 05, 2019
Alessandro Achille, Giovanni Paolini, Glen Mbeng, Stefano Soatto


  Access Paper or Ask Questions

Task2Vec: Task Embedding for Meta-Learning


Feb 10, 2019
Alessandro Achille, Michael Lam, Rahul Tewari, Avinash Ravichandran, Subhransu Maji, Charless Fowlkes, Stefano Soatto, Pietro Perona


  Access Paper or Ask Questions

Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies


Aug 20, 2018
Alessandro Achille, Tom Eccles, Loic Matthey, Christopher P. Burgess, Nick Watters, Alexander Lerchner, Irina Higgins


  Access Paper or Ask Questions

Emergence of Invariance and Disentanglement in Deep Representations


Jun 28, 2018
Alessandro Achille, Stefano Soatto

* Deep learning, neural network, representation, flat minima, information bottleneck, overfitting, generalization, sufficiency, minimality, sensitivity, information complexity, stochastic gradient descent, regularization, total correlation, PAC-Bayes 

  Access Paper or Ask Questions

Critical Learning Periods in Deep Neural Networks


May 15, 2018
Alessandro Achille, Matteo Rovere, Stefano Soatto


  Access Paper or Ask Questions

A Separation Principle for Control in the Age of Deep Learning


Nov 09, 2017
Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions

Information Dropout: Learning Optimal Representations Through Noisy Computation


Feb 12, 2017
Alessandro Achille, Stefano Soatto


  Access Paper or Ask Questions