deep neural networks
A class of neural networks with multiple layers that enable the modeling of complex patterns and representations in data, foundational in deep learning.
- A Closer Look at NTK Alignment: Linking Phase Transitions in Deep Image Regression
- A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
- ASGO: Adaptive Structured Gradient Optimization
- Adversary Aware Optimization for Robust Defense
- BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
- Block Coordinate Descent for Neural Networks Provably Finds Global Minima
- Boosting the Uniqueness of Neural Networks Fingerprints with Informative Triggers
- Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness
- Causal Discovery and Inference through Next-Token Prediction
- Computation and Memory-Efficient Model Compression with Gradient Reweighting
- Dataset Distillation of 3D Point Clouds via Distribution Matching
- Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
- Efficient Representativeness-Aware Coreset Selection
- Efficient and Generalizable Mixed-Precision Quantization via Topological Entropy
- Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum
- Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
- Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL
- Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
- Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions
- Generating and Checking DNN Verification Proofs
- Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization
- Hankel Singular Value Regularization for Highly Compressible State Space Models
- Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings
- Improving Deep Learning for Accelerated MRI With Data Filtering
- Learning Provably Improves the Convergence of Gradient Descent
- Learning in Compact Spaces with Approximately Normalized Transformer
- Learning to cluster neuronal function
- Manipulating Feature Visualizations with Gradient Slingshots
- Memorization in Graph Neural Networks
- Multi-Expert Distributionally Robust Optimization for Out-of-Distribution Generalization
- Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
- On the VC dimension of deep group convolutional neural networks
- Optimal Rates for Generalization of Gradient Descent for Deep ReLU Classification
- Parameter Dynamics of Online Machine Learning and Test-time Adaptation
- QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
- Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations
- Revisiting Residual Connections: Orthogonal Updates for Stable and Efficient Deep Networks
- Sequential Attention-based Sampling for Histopathological Analysis
- Sinusoidal Initialization, Time for a New Start
- Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness
- Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
- The Computational Advantage of Depth in Learning High-Dimensional Hierarchical Targets
- The Persistence of Neural Collapse Despite Low-Rank Bias
- The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
- Torch-Uncertainty: Deep Learning Uncertainty Quantification
- Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds
- Transformer brain encoders explain human high-level visual responses
- Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data
- Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks
- Variational Learning Finds Flatter Solutions at the Edge of Stability