Failure-mode index

Search what already failed

A searchable index of real negative results, null findings, and replication failures from the published literature — so you can learn what didn't work before repeating it.

All Replication Failure Negative / Null Result Report Failed Experiment Report Abandoned Hypothesis Methods Dead-End Short Note Null Dataset Protocol

WASTE indexes published research — it does not host or republish full papers. Each entry is a metadata record (title, authors, DOI) compiled from open scholarly databases, with the abstract shown in full only where the paper is openly licensed (e.g. Creative Commons); otherwise a short excerpt is shown for reference under fair use. WASTE classifies each work by failure type; classifications are automated and approximate.

By fieldMedicine 12,214 Computer Science 743 Biochemistry, Genetics and Molecular Biology 414 Social Sciences 302 Psychology 299 Physics 280 Neuroscience 243 Economics, Econometrics and Finance 196 Environmental Science 171 Mathematics 155 Agricultural and Biological Sciences 137 Engineering 135

3 results in Negative / Null Result Report for "hyperparameters"

Negative / Null Result ReportOpen accessComputer Science

Hyperparameters in Continual Learning: A Reality Check

Sungmin Cha, Kyunghyun Cho · 2024 · arXiv

Continual learning (CL) aims to train a model on a sequence of tasks (i.e., a CL scenario) while balancing the trade-off between plasticity (learning new tasks) and stability (retaining prior knowledge). The dominantly adopted conventional evaluation protocol for CL algorithms selects the best hyperparameters (e.g., learning rate, mini-batch size, regularization strengths, etc.) within a given scenario and then evaluates the algorithms using these hyperparameters in the same scenario. However, this protocol has significant shortcomings: it overestimates the CL capacity of algorithms and relies

View details →

Negative / Null Result ReportOpen accessMathematics

Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models

Courtney Paquette, Elliot Paquette · 2021 · arXiv

We analyze a class of stochastic gradient algorithms with momentum on a high-dimensional random least squares problem. Our framework, inspired by random matrix theory, provides an exact (deterministic) characterization for the sequence of loss values produced by these algorithms which is expressed only in terms of the eigenvalues of the Hessian. This leads to simple expressions for nearly-optimal hyperparameters, a description of the limiting neighborhood, and average-case complexity. As a consequence, we show that (small-batch) stochastic heavy-ball momentum with a fixed momentum parameter pr

View details →

Negative / Null Result ReportOpen accessComputer Science

Semantic Table Detection with LayoutLMv3

Ivan Silajev, Niels Victor, Phillip Mortimer · 2022 · arXiv

This paper presents an application of the LayoutLMv3 model for semantic table detection on financial documents from the IIIT-AR-13K dataset. The motivation behind this paper's experiment was that LayoutLMv3's official paper had no results for table detection using semantic information. We concluded that our approach did not improve the model's table detection capabilities, for which we can give several possible reasons. Either the model's weights were unsuitable for our purpose, or we needed to invest more time in optimising the model's hyperparameters. It is also possible that semantic inform

View details →