Search Results for author: Nicolo Fusi

Found 12 papers, 4 papers with code

On Hard Episodes in Meta-Learning

no code implementations21 Oct 2021 Samyadeep Basu, Amr Sharaf, Nicolo Fusi, Soheil Feizi

To address the issue of sub-par performance on hard episodes, we investigate and benchmark different meta-training strategies based on adversarial training and curriculum learning.

Curriculum Learning Meta-Learning

Rapid Model Architecture Adaption for Meta-Learning

no code implementations10 Sep 2021 Yiren Zhao, Xitong Gao, Ilia Shumailov, Nicolo Fusi, Robert Mullins

H-Meta-NAS shows a Pareto dominance compared to a variety of NAS and manual baselines in popular few-shot learning benchmarks with various hardware platforms and constraints.

Few-Shot Learning

HANT: Hardware-Aware Network Transformation

no code implementations12 Jul 2021 Pavlo Molchanov, Jimmy Hall, Hongxu Yin, Jan Kautz, Nicolo Fusi, Arash Vahdat

HANT tackles the problem in two phase: In the first phase, a large number of alternative operations per every layer of the teacher model is trained using layer-wise feature map distillation.

Neural Architecture Search Quantization

Model-specific Data Subsampling with Influence Functions

no code implementations20 Oct 2020 Anant Raj, Cameron Musco, Lester Mackey, Nicolo Fusi

Model selection requires repeatedly evaluating models on a given dataset and measuring their relative performances.

Model Selection

Weighted Meta-Learning

no code implementations20 Mar 2020 Diana Cai, Rishit Sheth, Lester Mackey, Nicolo Fusi

Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples.

Meta-Learning

Feature Gradients: Scalable Feature Selection via Discrete Relaxation

no code implementations27 Aug 2019 Rishit Sheth, Nicolo Fusi

In this paper we introduce Feature Gradients, a gradient-based search algorithm for feature selection.

Feature Selection

Model Compression with Generative Adversarial Networks

no code implementations ICLR 2019 Ruishan Liu, Nicolo Fusi, Lester Mackey

Our GAN-assisted model compression (GAN-MC) significantly improves student accuracy for expensive models such as deep neural networks and large random forests on both image and tabular datasets.

Image Classification Model Compression

Probabilistic Neural Architecture Search

no code implementations13 Feb 2019 Francesco Paolo Casale, Jonathan Gordon, Nicolo Fusi

We showcase the advantages of our approach in applications to CIFAR-10 and ImageNet, where our approach outperforms methods with double its computational cost and matches the performance of methods with costs that are three orders of magnitude larger.

Neural Architecture Search

Teacher-Student Compression with Generative Adversarial Networks

1 code implementation ICLR 2019 Ruishan Liu, Nicolo Fusi, Lester Mackey

Our GAN-assisted TSC (GAN-TSC) significantly improves student accuracy for expensive models such as large random forests and deep neural networks on both tabular and image datasets.

Image Classification Model Compression

Gaussian Process Prior Variational Autoencoders

2 code implementations NeurIPS 2018 Francesco Paolo Casale, Adrian V. Dalca, Luca Saglietti, Jennifer Listgarten, Nicolo Fusi

In this work, we introduce a new model, the Gaussian Process (GP) Prior Variational Autoencoder (GPPVAE), to specifically address this issue.

Time Series

Probabilistic Matrix Factorization for Automated Machine Learning

1 code implementation NeurIPS 2018 Nicolo Fusi, Rishit Sheth, Huseyn Melih Elibol

Automating the selection and tuning of machine learning pipelines consisting of data pre-processing methods and machine learning models, has long been one of the goals of the machine learning community.

Collaborative Filtering Meta-Learning +1

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