Search Results for author:
Found 26 papers, 17 papers with code
A Lie Group Approach to Riemannian Batch Normalization
Using the deformation concept, we generalize the existing Lie groups on SPD manifolds into three families of parameterized Lie groups.
ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
This paper explores a new post-hoc training-free compression paradigm for compressing Large Language Models (LLMs) to facilitate their wider adoption in various computing environments.
RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection
This observation motivates us to propose \texttt{RankFeat}, a simple yet effective \emph{post hoc} approach for OOD detection by removing the rank-1 matrix composed of the largest singular value and the associated singular vectors from the high-level feature.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Flow Factorized Representation Learning
A prominent goal of representation learning research is to achieve representations which are factorized in a useful manner with respect to the ground truth factors of variation.
Householder Projector for Unsupervised Latent Semantics Discovery
Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space.
Riemannian Multinomial Logistics Regression for SPD Neural Networks
Besides, our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks.
Latent Traversals in Generative Models as Potential Flows
In this work, we instead propose to model latent structures with a learned dynamic potential landscape, thereby performing latent traversals as the flow of samples down the landscape's gradient.
Adaptive Riemannian Metrics on SPD Manifolds
Symmetric Positive Definite (SPD) matrices have received wide attention in machine learning due to their intrinsic capacity of encoding underlying structural correlation in data.
Preventive-Corrective Cyber-Defense: Attack-Induced Region Minimization and Cybersecurity Margin Maximization
With any given cyber-defense resource, this paper proposes a preventive-corrective cyber-defense strategy, which minimizes the FDI attack-induced region in a preventive manner, followed by maximizing the cybersecurity margin in a corrective manner.
Stability Constrained OPF in Microgrids: A Chance Constrained Optimization Framework with Non-Gaussian Uncertainty
To figure out the stability issues brought by renewable energy sources (RES) with non-Gaussian uncertainties in isolated microgrids, this paper proposes a chance constrained stability constrained optimal power flow (CC-SC-OPF) model.
Orthogonal SVD Covariance Conditioning and Latent Disentanglement
Extensive experiments on visual recognition demonstrate that our methods can simultaneously improve covariance conditioning and generalization.
Bumpless Topology Transition
The topology transition problem of transmission networks is becoming increasingly crucial with topological flexibility more widely leveraged to promote high renewable penetration.
RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection
The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings.
Optimal Topology Transition
This aims to find the topology transition trajectory from an initial topology to a desired terminal topology, which optimizes certain transition performance and satisfies operational constraints.
Batch-efficient EigenDecomposition for Small and Medium Matrices
EigenDecomposition (ED) is at the heart of many computer vision algorithms and applications.
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality
Inserting an SVD meta-layer into neural networks is prone to make the covariance ill-conditioned, which could harm the model in the training stability and generalization abilities.
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition
Inspired by this observation, we propose a network branch dedicated to magnifying the importance of small eigenvalues.
Ranked #5 on
Fine-Grained Image Classification
on Stanford Dogs
Fine-Grained Image Classification
Fine-Grained Visual Categorization
+1
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers
In particular, MJP first shuffles the selected patches via our block-wise random jigsaw puzzle shuffle algorithm, and their corresponding PEs are occluded.
GBA: A Tuning-free Approach to Switch between Synchronous and Asynchronous Training for Recommendation Model
High-concurrency asynchronous training upon parameter server (PS) architecture and high-performance synchronous training upon all-reduce (AR) architecture are the most commonly deployed distributed training modes for recommendation models.
PICASSO: Unleashing the Potential of GPU-centric Training for Wide-and-deep Recommender Systems
However, we observe that GPU devices in training recommender systems are underutilized, and they cannot attain an expected throughput improvement as what it has achieved in CV and NLP areas.
Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling
Specifically, the detail modeling focuses on capturing the object edges by supervision of explicitly decomposed detail label that consists of the pixels that are nested on the edge and near the edge.
Formulating Connectedness in Security-Constrained Optimal Transmission Switching Problems
This paper focuses on the issue of network connectedness (NC) in security-constrained optimal transmission switching problems, which is complicated by branch contingencies and corrective line switching.
Fast Differentiable Matrix Square Root and Inverse Square Root
Computing the matrix square root and its inverse in a differentiable manner is important in a variety of computer vision tasks.
Fast Differentiable Matrix Square Root
Previous methods either adopt the Singular Value Decomposition (SVD) to explicitly factorize the matrix or use the Newton-Schulz iteration (NS iteration) to derive the approximate solution.
Chance Constrained Economic Dispatch Considering the Capability of Network Flexibility Against Renewable Uncertainties
In the proposed model, both power generations and line susceptances are continuous variables to minimize the expected generation cost and guarantee a low probability of constraint violation in terms of generations and line flows under renewable uncertainties.
Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?
Singular Value Decomposition (SVD) is used in GCP to compute the matrix square root.
