A Meta-Learning Approach to Predicting Performance and Data Requirements
- URL: http://arxiv.org/abs/2303.01598v1
- Date: Thu, 2 Mar 2023 21:48:22 GMT
- Title: A Meta-Learning Approach to Predicting Performance and Data Requirements
- Authors: Achin Jain, Gurumurthy Swaminathan, Paolo Favaro, Hao Yang, Avinash
Ravichandran, Hrayr Harutyunyan, Alessandro Achille, Onkar Dabeer, Bernt
Schiele, Ashwin Swaminathan, Stefano Soatto
- Abstract summary: We propose an approach to estimate the number of samples required for a model to reach a target performance.
We find that the power law, the de facto principle to estimate model performance, leads to large error when using a small dataset.
We introduce a novel piecewise power law (PPL) that handles the two data differently.
- Score: 163.4412093478316
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose an approach to estimate the number of samples required for a model
to reach a target performance. We find that the power law, the de facto
principle to estimate model performance, leads to large error when using a
small dataset (e.g., 5 samples per class) for extrapolation. This is because
the log-performance error against the log-dataset size follows a nonlinear
progression in the few-shot regime followed by a linear progression in the
high-shot regime. We introduce a novel piecewise power law (PPL) that handles
the two data regimes differently. To estimate the parameters of the PPL, we
introduce a random forest regressor trained via meta learning that generalizes
across classification/detection tasks, ResNet/ViT based architectures, and
random/pre-trained initializations. The PPL improves the performance estimation
on average by 37% across 16 classification and 33% across 10 detection
datasets, compared to the power law. We further extend the PPL to provide a
confidence bound and use it to limit the prediction horizon that reduces
over-estimation of data by 76% on classification and 91% on detection datasets.
Related papers
- Scaling Laws for Predicting Downstream Performance in LLMs [75.28559015477137]
This work focuses on the pre-training loss as a more-efficient metric for performance estimation.
We extend the power law analytical function to predict domain-specific pre-training loss based on FLOPs across data sources.
We employ a two-layer neural network to model the non-linear relationship between multiple domain-specific loss and downstream performance.
arXiv Detail & Related papers (2024-10-11T04:57:48Z) - F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data [65.6499834212641]
We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm.
By considering domain similarities through task-specific metadata, our model improved generalization, where the excess risk decreases as the number of training tasks increases.
Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.
arXiv Detail & Related papers (2024-06-23T21:28:50Z) - It's all about PR -- Smart Benchmarking AI Accelerators using Performance Representatives [40.197673152937256]
Training of statistical performance models often requires vast amounts of data, leading to a significant time investment and can be difficult in case of limited hardware availability.
We propose a novel performance modeling methodology that significantly reduces the number of training samples while maintaining good accuracy.
We achieve a Mean Absolute Percentage Error (MAPE) of as low as 0.02% for single-layer estimations and 0.68% for whole estimations with less than 10000 training samples.
arXiv Detail & Related papers (2024-06-12T15:34:28Z) - Few-Shot Load Forecasting Under Data Scarcity in Smart Grids: A Meta-Learning Approach [0.18641315013048293]
This paper proposes adapting an established model-agnostic meta-learning algorithm for short-term load forecasting.
The proposed method can rapidly adapt and generalize within any unknown load time series of arbitrary length.
The proposed model is evaluated using a dataset of historical load consumption data from real-world consumers.
arXiv Detail & Related papers (2024-06-09T18:59:08Z) - Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation [62.2436697657307]
Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data.
We propose a method called Stratified Prediction-Powered Inference (StratPPI)
We show that the basic PPI estimates can be considerably improved by employing simple data stratification strategies.
arXiv Detail & Related papers (2024-06-06T17:37:39Z) - Sequential Learning Of Neural Networks for Prequential MDL [18.475866691786695]
We evaluate approaches for computing prequential description lengths for image classification datasets with neural networks.
Considering the computational cost, we find that online-learning with rehearsal has favorable performance.
We present description lengths for a suite of image classification datasets that improve upon previously reported results by large margins.
arXiv Detail & Related papers (2022-10-14T16:30:23Z) - Learning to be a Statistician: Learned Estimator for Number of Distinct
Values [54.629042119819744]
Estimating the number of distinct values (NDV) in a column is useful for many tasks in database systems.
In this work, we focus on how to derive accurate NDV estimations from random (online/offline) samples.
We propose to formulate the NDV estimation task in a supervised learning framework, and aim to learn a model as the estimator.
arXiv Detail & Related papers (2022-02-06T15:42:04Z) - Self-Supervised Pre-Training for Transformer-Based Person
Re-Identification [54.55281692768765]
Transformer-based supervised pre-training achieves great performance in person re-identification (ReID)
Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance.
This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
arXiv Detail & Related papers (2021-11-23T18:59:08Z) - Complementary Ensemble Learning [1.90365714903665]
We derive a technique to improve performance of state-of-the-art deep learning models.
Specifically, we train auxiliary models which are able to complement state-of-the-art model uncertainty.
arXiv Detail & Related papers (2021-11-09T03:23:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.