Gradient descent in deep networks implicitly drives features toward target-linear structure as captured by the weight Gram matrix and a derived virtual covariance.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
Presents a model-based proximal framework for adaptive momentum in first-order optimizers by using a two-plane approximation of the objective to dynamically set the memory coefficient online.
MICON integrates chemical structures as treatments into contrastive pre-training to enhance image representations for morphological profiling, yielding small but consistent gains over image-only baselines in cross-replicate and cross-center reproducibility tasks.
A comprehensive benchmark study of offline imitation learning methods on multi-stage robot manipulation tasks identifies key sensitivities to algorithm design, data quality, and stopping criteria while releasing all datasets and code.
QSurv uses Gauss-Legendre numerical quadrature and time-conditioned low-rank adaptation to enable scalable nonparametric continuous-time survival modeling with theoretical error bounds.
CPCANet unrolls the Flury-Gautschi algorithm for Common Principal Component Analysis into differentiable layers to learn a shared invariant subspace across domains, reporting SOTA zero-shot transfer on four DG benchmarks.
citing papers explorer
-
The Weight Gram Matrix Captures Sequential Feature Linearization in Deep Networks
Gradient descent in deep networks implicitly drives features toward target-linear structure as captured by the weight Gram matrix and a derived virtual covariance.
-
Probing Intrinsic Medical Task Relationships: A Contrastive Learning Perspective
TaCo contrastively embeds semantic, generative, and transformation tasks from medical imaging into a joint space to reveal which tasks cluster, blend, or remain distinct.
-
Adaptive Memory Momentum via a Model-Based Framework for Deep Learning Optimization
Presents a model-based proximal framework for adaptive momentum in first-order optimizers by using a two-plane approximation of the objective to dynamically set the memory coefficient online.
-
Integrating chemical structures as treatments improves representations of microscopy images for morphological profiling
MICON integrates chemical structures as treatments into contrastive pre-training to enhance image representations for morphological profiling, yielding small but consistent gains over image-only baselines in cross-replicate and cross-center reproducibility tasks.
-
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
A comprehensive benchmark study of offline imitation learning methods on multi-stage robot manipulation tasks identifies key sensitivities to algorithm design, data quality, and stopping criteria while releasing all datasets and code.
-
A Scalable Nonparametric Continuous-Time Survival Model through Numerical Quadrature
QSurv uses Gauss-Legendre numerical quadrature and time-conditioned low-rank adaptation to enable scalable nonparametric continuous-time survival modeling with theoretical error bounds.
-
CPCANet: Deep Unfolding Common Principal Component Analysis for Domain Generalization
CPCANet unrolls the Flury-Gautschi algorithm for Common Principal Component Analysis into differentiable layers to learn a shared invariant subspace across domains, reporting SOTA zero-shot transfer on four DG benchmarks.