paper-with-me

Papers

Notes on Latent Structure Models and SPIGOT

2019-07-24 · André F. T. Martins, Vlad Niculae

These notes aim to shed light on the recently proposed structured projected intermediate gradient optimization technique (SPIGOT, Peng et al., 2018). SPIGOT is a variant of the straight-through estimator (Bengio et al., 2013) which bypasses gradients of the argmax function by back-propagating a surrogate "gradient." We provide a new interpretation to the proposed gradient and put this technique into perspective, linking it to other methods for training neural networks with discrete latent variables. As a by-product, we suggest alternate variants of SPIGOT which will be further explored in future work.

📄 PDF Abstract BibTeX arXiv:1907.10348

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Backpropagating through Structured Argmax using a SPIGOT

2018-05-12 · ACL 2018 7 · Hao Peng, Sam Thomson, Noah A. Smith

We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decision structured predictions (e.g., parsing)…

Dependency ParsingReinforcement LearningSemantic Dependency ParsingSemantic Parsing+2

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning

2020-10-05 · EMNLP 2020 11 · Tsvetomila Mihaylova, Vlad Niculae, André F. T. Martins

Latent structure models are a powerful tool for modeling language data: they can mitigate the error propagation and annotation bottleneck in pipeline systems, while simultaneously uncovering linguistic insights about the…

pixelLOG: Logging of Online Gameplay for Cognitive Research

2026-02-09 · Zeyu Lu, Dennis L. Barbour arxiv

Traditional cognitive assessments often rely on isolated, output-focused measurements that may fail to capture the complexity of human cognition in naturalistic settings. We present pixelLOG, a high-performance data coll…

Computing patient similarity based on unstructured clinical notes

2026-01-12 · Petr Zelina, Marko Řeháček, Jana Halámková, Lucia Bohovicová 외 arxiv

Clinical notes hold rich yet unstructured details about diagnoses, treatments, and outcomes that are vital to precision medicine but hard to exploit at scale. We introduce a method that represents each patient as a matri…

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs

2025-07-27 · Raj Krishnan Vijayaraj arxiv

LLMs for clinical decision support often fail under small but clinically meaningful input shifts such as masking a symptom or negating a finding, despite high performance on static benchmarks. These reasoning failures fr…