eGAD! double descent is explained by Generalized Aliasing Decomposition
- URL: http://arxiv.org/abs/2408.08294v3
- Date: Fri, 10 Jan 2025 00:19:23 GMT
- Title: eGAD! double descent is explained by Generalized Aliasing Decomposition
- Authors: Mark K. Transtrum, Gus L. W. Hart, Tyler J. Jarvis, Jared P. Whitehead,
- Abstract summary: We introduce a novel decomposition that we call the generalized aliasing decomposition (GAD) to explain the relationship between predictive performance and model complexity.
GAD decomposes the predictive error into three parts: 1) model insufficiency, which dominates when the number of parameters is much smaller than the number of data points, 2) data insufficiency, which dominates when the number of parameters is much greater than the number of data points, and 3) generalized aliasing, which dominates between these two extremes.
- Score: 0.0
- License:
- Abstract: A central problem in data science is to use potentially noisy samples of an unknown function to predict values for unseen inputs. In classical statistics, predictive error is understood as a trade-off between the bias and the variance that balances model simplicity with its ability to fit complex functions. However, over-parameterized models exhibit counterintuitive behaviors, such as "double descent" in which models of increasing complexity exhibit decreasing generalization error. Others may exhibit more complicated patterns of predictive error with multiple peaks and valleys. Neither double descent nor multiple descent phenomena are well explained by the bias-variance decomposition. We introduce a novel decomposition that we call the generalized aliasing decomposition (GAD) to explain the relationship between predictive performance and model complexity. The GAD decomposes the predictive error into three parts: 1) model insufficiency, which dominates when the number of parameters is much smaller than the number of data points, 2) data insufficiency, which dominates when the number of parameters is much greater than the number of data points, and 3) generalized aliasing, which dominates between these two extremes. We demonstrate the applicability of the GAD to diverse applications, including random feature models from machine learning, Fourier transforms from signal processing, solution methods for differential equations, and predictive formation enthalpy in materials discovery. Because key components of the GAD can be explicitly calculated from the relationship between model class and samples without seeing any data labels, it can answer questions related to experimental design and model selection before collecting data or performing experiments. We further demonstrate this approach on several examples and discuss implications for predictive modeling and data science.
Related papers
- Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learning [6.278498348219108]
We revisit model complexity from first principles, by first reinterpreting and then extending the classical statistical concept of (effective) degrees of freedom.
We demonstrate the utility of our proposed complexity measures through a mix of conceptual arguments, theory, and experiments.
arXiv Detail & Related papers (2024-10-02T06:09:57Z) - Scaling and renormalization in high-dimensional regression [72.59731158970894]
This paper presents a succinct derivation of the training and generalization performance of a variety of high-dimensional ridge regression models.
We provide an introduction and review of recent results on these topics, aimed at readers with backgrounds in physics and deep learning.
arXiv Detail & Related papers (2024-05-01T15:59:00Z) - Sample, estimate, aggregate: A recipe for causal discovery foundation models [28.116832159265964]
We train a supervised model that learns to predict a larger causal graph from the outputs of classical causal discovery algorithms run over subsets of variables.
Our approach is enabled by the observation that typical errors in the outputs of classical methods remain comparable across datasets.
Experiments on real and synthetic data demonstrate that this model maintains high accuracy in the face of misspecification or distribution shift.
arXiv Detail & Related papers (2024-02-02T21:57:58Z) - Analysis of Interpolating Regression Models and the Double Descent
Phenomenon [3.883460584034765]
It is commonly assumed that models which interpolate noisy training data are poor to generalize.
The best models obtained are overparametrized and the testing error exhibits the double descent behavior as the model order increases.
We derive a result based on the behavior of the smallest singular value of the regression matrix that explains the peak location and the double descent shape of the testing error as a function of model order.
arXiv Detail & Related papers (2023-04-17T09:44:33Z) - Double Descent Demystified: Identifying, Interpreting & Ablating the
Sources of a Deep Learning Puzzle [12.00962791565144]
Double descent is a surprising phenomenon in machine learning.
As the number of model parameters grows relative to the number of data, test error drops.
arXiv Detail & Related papers (2023-03-24T17:03:40Z) - On the Strong Correlation Between Model Invariance and Generalization [54.812786542023325]
Generalization captures a model's ability to classify unseen data.
Invariance measures consistency of model predictions on transformations of the data.
From a dataset-centric view, we find a certain model's accuracy and invariance linearly correlated on different test sets.
arXiv Detail & Related papers (2022-07-14T17:08:25Z) - Amortized Inference for Causal Structure Learning [72.84105256353801]
Learning causal structure poses a search problem that typically involves evaluating structures using a score or independence test.
We train a variational inference model to predict the causal structure from observational/interventional data.
Our models exhibit robust generalization capabilities under substantial distribution shift.
arXiv Detail & Related papers (2022-05-25T17:37:08Z) - X-model: Improving Data Efficiency in Deep Learning with A Minimax Model [78.55482897452417]
We aim at improving data efficiency for both classification and regression setups in deep learning.
To take the power of both worlds, we propose a novel X-model.
X-model plays a minimax game between the feature extractor and task-specific heads.
arXiv Detail & Related papers (2021-10-09T13:56:48Z) - Memorizing without overfitting: Bias, variance, and interpolation in
over-parameterized models [0.0]
The bias-variance trade-off is a central concept in supervised learning.
Modern Deep Learning methods flout this dogma, achieving state-of-the-art performance.
arXiv Detail & Related papers (2020-10-26T22:31:04Z) - Deducing neighborhoods of classes from a fitted model [68.8204255655161]
In this article a new kind of interpretable machine learning method is presented.
It can help to understand the partitioning of the feature space into predicted classes in a classification model using quantile shifts.
Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed.
arXiv Detail & Related papers (2020-09-11T16:35:53Z) - Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers.
We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model.
Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
arXiv Detail & Related papers (2020-06-22T21:12:31Z)
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.