Search Results for author: Nicolo Fusi

Found 18 papers, 6 papers with code

Gaussian Processes for Big Data

8 code implementations26 Sep 2013 James Hensman, Nicolo Fusi, Neil D. Lawrence

We introduce stochastic variational inference for Gaussian process models.

Gaussian Processes Variational Inference

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.

Bayesian Optimization BIG-bench Machine Learning +3

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 Time Series Analysis

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.

Generative Adversarial Network Image Classification +1

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

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.

Generative Adversarial Network Image Classification +1

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

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

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.

BIG-bench Machine Learning Model Selection

LANA: Latency Aware Network Acceleration

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

We analyze three popular network architectures: EfficientNetV1, EfficientNetV2 and ResNeST, and achieve accuracy improvement for all models (up to $3. 0\%$) when compressing larger models to the latency level of smaller models.

Neural Architecture Search Quantization

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

Hardware-Aware Network Transformation

no code implementations29 Sep 2021 Pavlo Molchanov, Jimmy Hall, Hongxu Yin, Jan Kautz, Nicolo Fusi, Arash Vahdat

In the second phase, it solves the combinatorial selection of efficient operations using a novel constrained integer linear optimization approach.

Neural Architecture Search

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.

Meta-Learning

Bayesian Optimization Over Iterative Learners with Structured Responses: A Budget-aware Planning Approach

no code implementations25 Jun 2022 Syrine Belakaria, Janardhan Rao Doppa, Nicolo Fusi, Rishit Sheth

The rising growth of deep neural networks (DNNs) and datasets in size motivates the need for efficient solutions for simultaneous model selection and training.

Bayesian Optimization Hyperparameter Optimization +1

Interpretable Distribution Shift Detection using Optimal Transport

no code implementations4 Aug 2022 Neha Hulkund, Nicolo Fusi, Jennifer Wortman Vaughan, David Alvarez-Melis

We propose a method to identify and characterize distribution shifts in classification datasets based on optimal transport.

Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains

1 code implementation6 Feb 2024 Junhong Shen, Neil Tenenholtz, James Brian Hall, David Alvarez-Melis, Nicolo Fusi

Large Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language.

TAG Zero-shot Generalization

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