# TAPAS: Two-pass Approximate Adaptive Sampling for Softmax

arXiv: https://arxiv.org/abs/1707.03073 · HTML: https://mlsanity.com/paper/1707.03073/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2017.

## Built on by (most cited first, 3 of 3)

- [Item Recommendation from Implicit Feedback](https://mlsanity.com/paper/2101.08769/) (2021)
- [Prototype Memory for Large-scale Face Representation Learning](https://mlsanity.com/paper/2105.02103/) (2021)
- [DecompressionLM: Deterministic, Diagnostic, and Zero-Shot Concept Graph Extraction from Language Models](https://mlsanity.com/paper/2602.00377/) (2026)

## Abstract (arXiv)

TAPAS is a novel adaptive sampling method for the softmax model. It uses a two pass sampling strategy where the examples used to approximate the gradient of the partition function are first sampled according to a squashed population distribution and then resampled adaptively using the context and current model. We describe an efficient distributed implementation of TAPAS. We show, on both synthetic data and a large real dataset, that TAPAS has low computational overhead and works well for minimizing the rank loss for multi-class classification problems with a very large label space.