Negative / Null Result ReportOpen accessComputer Science
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
Negative / Null Result ReportOpen accessMathematics
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
Negative / Null Result ReportOpen accessComputer Science
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
