conftrace_
← Optimization & Theory
Deep Learning › Optimization & Theory ›

Neural Network Optimization

903 papers

Papers per year

2
9
127
100
'10
'15
'20
'25

Papers

Controlling Continuous Relaxation for Combinatorial Optimization NIPS 2024
Stepping on the Edge: Curvature Aware Learning Rate Tuners NIPS 2024
Monomial Matrix Group Equivariant Neural Functional Networks NIPS 2024
Achieving Domain-Independent Certified Robustness via Knowledge Continuity NIPS 2024
Towards the Dynamics of a DNN Learning Symbolic Interactions NIPS 2024
SAMPa: Sharpness-aware Minimization Parallelized NIPS 2024
Provable Tempered Overfitting of Minimal Nets and Typical Nets NIPS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
LoRA-GA: Low-Rank Adaptation with Gradient Approximation NIPS 2024
Abrupt Learning in Transformers: A Case Study on Matrix Completion NIPS 2024
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning NIPS 2024
Where Do Large Learning Rates Lead Us? NIPS 2024
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit NIPS 2024
Continual learning with the neural tangent ensemble NIPS 2024
Swift Sampler: Efficient Learning of Sampler by 10 Parameters NIPS 2024
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment NIPS 2024
Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance NIPS 2024
SGD vs GD: Rank Deficiency in Linear Networks NIPS 2024
On the Limitations of Fractal Dimension as a Measure of Generalization NIPS 2024
PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization NIPS 2024
Nature-Inspired Local Propagation NIPS 2024
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks NIPS 2024
BMRS: Bayesian Model Reduction for Structured Pruning NIPS 2024
Memory-Efficient LLM Training with Online Subspace Descent NIPS 2024
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level NIPS 2024