Search Results for author:
Found 23 papers, 6 papers with code
OpenTensor: Reproducing Faster Matrix Multiplication Discovering Algorithms
OpenTensor is a reproduction of AlphaTensor, which discovered a new algorithm that outperforms the state-of-the-art methods for matrix multiplication by Deep Reinforcement Learning (DRL).
Elementary Analysis of Policy Gradient Methods
Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning.
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation
Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety.
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction
Document image dewarping is a crucial task in computer vision with numerous practical applications.
Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning
Secondly, we develop a series of affinity learning methods that equip the selfexpressive framework with ℓp-norm to construct an intrinsic affinity matrix with an adaptive extension.
Highly-Efficient Robinson-Foulds Distance Estimation with Matrix Correction
Phylogenetic trees are essential in studying evolutionary relationships, and the Robinson-Foulds (RF) distance is a widely used metric to calculate pairwise dissimilarities between phylogenetic trees, with various applications in both the biology and computing communities.
Online Estimation of Similarity Matrices with Incomplete Data
To address this challenge, we propose matrix correction algorithms that leverage the positive semi-definiteness (PSD) of the similarity matrix to improve similarity estimation in both offline and online scenarios.
Metric Nearness Made Practical
The first stage computes a fast yet high-quality approximate solution from a set of isometrically embeddable metrics, further improved by an effective heuristic.
S-NeRF: Neural Radiance Fields for Street Views
Specifically, we improve the scene parameterization function and the camera poses for learning better neural representations from street views.
MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking
Then, the noised previous state is used as the input to learn to predict the current state, improving the model's ability to update and correct slot values.
CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking
The unlabeled data of the DST task is incorporated into the self-training iterations, where the pseudo labels are predicted by a DST model trained on limited labeled data in advance.
Personalizing or Not: Dynamically Personalized Federated Learning with Incentives
This dynamically personalized FL technique incentivizes clients to participate in personalizing local models while allowing the adoption of the global model when it performs better.
POViT: Vision Transformer for Multi-objective Design and Characterization of Nanophotonic Devices
In this work, we propose the first-ever Transformer model (POViT) to efficiently design and simulate semiconductor photonic devices with multiple objectives.
Federated Two-stage Learning with Sign-based Voting
In this paper, we design a federated two-stage learning framework that augments prototypical federated learning with a cut layer on devices and uses sign-based stochastic gradient descent with the majority vote method on model updates.
Towards Heterogeneous Clients with Elastic Federated Learning
Training in heterogeneous and potentially massive networks introduces bias into the system, which is originated from the non-IID data and the low participation rate in reality.
The simpler the better: vanilla sgd revisited
The stochastic gradient descent (SGD) method, first proposed in 1950's, has been the foundation for deep-neural-network (DNN) training with numerous enhancements including adding a momentum or adaptively selecting learning rates, or using both strategies and more.
Binary Random Projections with Controllable Sparsity Patterns
Random projection is often used to project higher-dimensional vectors onto a lower-dimensional space, while approximately preserving their pairwise distances.
Sparse Lifting of Dense Vectors: Unifying Word and Sentence Representations
As the first step in automated natural language processing, representing words and sentences is of central importance and has attracted significant research attention.
An Augmented Transformer Architecture for Natural Language Generation Tasks
The Transformer based neural networks have been showing significant advantages on most evaluations of various natural language processing and other sequence-to-sequence tasks due to its inherent architecture based superiorities.
Modeling Winner-Take-All Competition in Sparse Binary Projections
Inspired by the advances in biological science, the study of sparse binary projection models has attracted considerable recent research attention.
AuxBlocks: Defense Adversarial Example via Auxiliary Blocks
Deep learning models are vulnerable to adversarial examples, which poses an indisputable threat to their applications.
Fast Similarity Search via Optimal Sparse Lifting
Similarity search is a fundamental problem in computing science with various applications and has attracted significant research attention, especially in large-scale search with high dimensions.
Estimating Jaccard Index with Missing Observations: A Matrix Calibration Approach
The Jaccard index is a standard statistics for comparing the pairwise similarity between data samples.
