conftrace_
← Optimization & Theory
Machine Learning › Optimization & Theory ›

Neural Network Optimization

3,648 papers

Papers per year

Papers

Sharpened Lazy Incremental Quasi-Newton Method AISTATS 2024
Data Driven Threshold and Potential Initialization for Spiking Neural Networks AISTATS 2024
Revisiting the Noise Model of Stochastic Gradient Descent AISTATS 2024
Parameter-Agnostic Optimization under Relaxed Smoothness AISTATS 2024
Provable Accelerated Convergence of Nesterov’s Momentum for Deep ReLU Neural Networks ALT 2024
Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization ALT 2024
Improving Adaptive Online Learning Using Refined Discretization ALT 2024
CEPT: A Contrast-Enhanced Prompt-Tuning Framework for Emotion Recognition in Conversation COLING 2024
Context-Aware Non-Autoregressive Document-Level Translation with Sentence-Aligned Connectionist Temporal Classification COLING 2024
Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification COLING 2024
DET: A Dual-Encoding Transformer for Relational Graph Embedding COLING 2024
EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks COLING 2024
Enhancing Distantly Supervised Named Entity Recognition with Strong Label Guided Lottery Training COLING 2024
Enhancing Parameter-efficient Fine-tuning with Simple Calibration Based on Stable Rank COLING 2024
Information Extraction with Differentiable Beam Search on Graph RNNs COLING 2024
Jump to Conclusions: Short-Cutting Transformers with Linear Transformations COLING 2024
On the Relationship between Skill Neurons and Robustness in Prompt Tuning COLING 2024
The Open-World Lottery Ticket Hypothesis for OOD Intent Classification COLING 2024
Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection COLING 2024
Efficiently Learning One-Hidden-Layer ReLU Networks via SchurPolynomials COLT 2024
Exact Mean Square Linear Stability Analysis for SGD COLT 2024
Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality (extended abstract) COLT 2024
Open Problem: Black-Box Reductions and Adaptive Gradient Methods for Nonconvex Optimization COLT 2024
Gradient-based Parameter Selection for Efficient Fine-Tuning CVPR 2024
From Activation to Initialization: Scaling Insights for Optimizing Neural Fields CVPR 2024