activity
20162026
most citedLearning in the Recurrent State: Gradient Descent with Linear Recurrent Networks

1 citations · 4 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2024★ 1 cited

Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks

Yudou Tian, Neeraj Mohan Sushma, Harshvardhan Mestha +3

Linear recurrent networks (LRNNs) offer linear-time sequence modeling, but standard recurrent updates do not directly expose the supervised products needed for in-context gradient…

cs.LG2024★ 1 cited

Entropy Reweighted Conformal Classification

Rui Luo, Nicolo Colombo

Conformal Prediction (CP) is a powerful framework for constructing prediction sets with guaranteed coverage. However, recent studies have shown that integrating confidence calibrat…

cs.LG2024

Normalizing Flows for Conformal Regression

Nicolo Colombo

Conformal Prediction (CP) algorithms estimate the uncertainty of a prediction model by calibrating its outputs on labeled data. The same calibration scheme usually applies to any m…

cs.LG2024

Conformal Load Prediction with Transductive Graph Autoencoders

Rui Luo, Nicolo Colombo

Predicting edge weights on graphs has various applications, from transportation systems to social networks. This paper describes a Graph Neural Network (GNN) approach for edge weig…

cs.LG2023

On training locally adaptive CP

Nicolo Colombo

We address the problem of making Conformal Prediction (CP) intervals locally adaptive. Most existing methods focus on approximating the object-conditional validity of the intervals…

cs.LG2021

Differentiable Architecture Pruning for Transfer Learning

Nicolo Colombo, Yang Gao

We propose a new gradient-based approach for extracting sub-architectures from a given large model. Contrarily to existing pruning methods, which are unable to disentangle the netw…