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

Neural Network Optimization

3,648 papers

Papers per year

Papers

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models EMNLP 2024
HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy EMNLP 2024
Recurrent neural networks: vanishing and exploding gradients are not the end of the story NIPS 2024
Deep Learning for Computing Convergence Rates of Markov Chains NIPS 2024
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks NIPS 2024
Parameter-Agnostic Optimization under Relaxed Smoothness AISTATS 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NIPS 2024
Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting AAAI 2024
Chain-of-Thought Reasoning Without Prompting NIPS 2024
Investigating Acceleration of LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with ‘LITE’ NAACL 2024
Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence AISTATS 2024
Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent JMLR 2024
Tending Towards Stability: Convergence Challenges in Small Language Models EMNLP 2024
Adaptive Sharpness-Aware Pruning for Robust Sparse Networks ICLR 2024
Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths EMNLP 2024
Ordered Momentum for Asynchronous SGD NIPS 2024
A Structure-Aware Framework for Learning Device Placements on Computation Graphs NIPS 2024
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics NIPS 2024
Vision Mamba Mender NIPS 2024
Linguistic Fingerprint in Transformer Models: How Language Variation Influences Parameter Selection in Irony Detection COLING 2024
Beyond Slow Signs in High-fidelity Model Extraction NIPS 2024
Batch Normalization Is Blind to the First and Second Derivatives of the Loss AAAI 2024
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective NIPS 2024
Beyond Fine-tuning: Unleashing the Potential of Continuous Pretraining for Clinical LLMs. EMNLP 2024
Preparing Lessons for Progressive Training on Language Models AAAI 2024