conftrace_

forward-mode differentiation

5 papers

Explore in graph

Also known as

FMD

Co-occurring keywords · papers mentioning both

hyperparameter optimization (2) few-shot learning (2) stochastic gradient descent (2) ordinary differential equation (1) language model fine-tuning (1) loss surface (1) gradient-based meta-learning (1) large language model (1) gpu parallelism (1) forward-mode automatic differentiation (1)

Papers

Second-order forward-mode optimization of recurrent neural networks for neuroscience NeurIPS 2024 Thinking Forward: Memory-Efficient Federated Finetuning of Language Models NeurIPS 2024 Continuous-Time Meta-Learning with Forward Mode Differentiation ICLR 2022 Gradient-based Hyperparameter Optimization Over Long Horizons NeurIPS 2021 Forward and Reverse Gradient-Based Hyperparameter Optimization ICML 2017