Pedro Savarese
9 papers · 2019–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π§ Keyword Pioneer π Conference Polyglot (4) π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (22)
π£
Hot Topic Early Bird
π
Keyword Champion
(2)
ποΈ
Keyword Collector
(51)
β
The Questioner
π₯
Unstoppable
(5)
Conferences
NIPS (4)
COLT (2)
CVPR (2)
ICLR (1)
Top co-authors
Keywords
neural network
(3)
learning rate adaptation
(2)
model compression
(1)
neural network compression
(1)
neural network pruning
(1)
representation learning
(1)
image classification
(1)
gradient descent
(1)
stochastic gradient descent
(1)
semantic segmentation
(1)
image segmentation
(1)
few-shot learning
(1)
online learning
(1)
function approximation
(1)
efficient computing
(1)
lottery ticket hypothesis
(1)
unsupervised segmentation
(1)
parameter optimization
(1)
unsupervised learning
(1)
neural network quantization
(1)
Papers
Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
NIPS 2023
Not All Bits have Equal Value: Heterogeneous Precisions via Trainable Noise
NIPS 2022
Domain-Independent Dominance of Adaptive Methods
CVPR 2021
Online Meta-Learning via Learning with Layer-Distributed Memory
NIPS 2021
Information-Theoretic Segmentation by Inpainting Error Maximization
CVPR 2021
Winning the Lottery with Continuous Sparsification
NIPS 2020
Kernel and Rich Regimes in Overparametrized Models
COLT 2020
Learning Implicitly Recurrent CNNs Through Parameter Sharing
ICLR 2019
How do infinite width bounded norm networks look in function space?
COLT 2019