ARSM Gradient Estimator for Supervised Learning to Rank
We propose a new model for supervised learning to rank. In our model, the relevance labels are assumed to follow a categorical distribution whose probabilities are constructed based on a scoring function. We optimize the training objective with respect to the multivariate categorical variables with an unbiased and low-variance gradient estimator. Learning-to-rank methods can generally be categorized into pointwise, pairwise, and listwise approaches. Although our scoring function is pointwise, the proposed framework permits flexibility over the choice of the loss function. In our new model, the loss function need not be differentiable and can either be pointwise or listwise. Our proposed method achieves better or comparable results on two datasets compared with existing pairwise and listwise methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Learning-To-RankSimilar Papers 제목 키워드 기반
ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables
To address the challenge of backpropagating the gradient through categorical variables, we propose the augment-REINFORCE-swap-merge (ARSM) gradient estimator that is unbiased and has low variance. ARSM first uses variabl…
MazeNet: An Accurate, Fast, and Scalable Deep Learning Solution for Steiner Minimum Trees
The Obstacle Avoiding Rectilinear Steiner Minimum Tree (OARSMT) problem, which seeks the shortest interconnection of a given number of terminals in a rectilinear plane while avoiding obstacles, is a critical task in inte…
PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training
Accelerator memory and networking constraints have emerged as dominant bottlenecks when training large language models LLMs with billions of parameters. Existing low rank gradient estimators such as GaLoRE and FLORA comp…
Optimal low-rank stochastic gradient estimation for LLM training
Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical evidence that many LLM gradient matrice…
Boosted Stochastic Frank-Wolfe for Constrained Nonconvex Optimization
The boosted Frank-Wolfe algorithm accelerates the classical Frank-Wolfe algorithm by better aligning the update direction with the negative gradient. Its analysis, however, has been limited to deterministic convex proble…