Measuring model variability using robust non-parametric testing

• URL: http://arxiv.org/abs/2406.08307v1
• Date: Wed, 12 Jun 2024 15:08:15 GMT
• Title: Measuring model variability using robust non-parametric testing
• Authors: Sinjini Banerjee, Tim Marrinan, Reilly Cannon, Tony Chiang, Anand D. Sarwate,
• Abstract summary: This work attempts to describe the relationship between deep net models trained with different random seeds and the behavior of the expected model. We propose a novel summary statistic for network similarity, referred to as the $alpha$-trimming level. We show that the $alpha$-trimming level is more expressive than different performance metrics like validation accuracy, churn, or expected calibration error when taken alone.
• Score: 5.519968037738177
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training a deep neural network often involves stochastic optimization, meaning each run will produce a different model. The seed used to initialize random elements of the optimization procedure heavily influences the quality of a trained model, which may be obscure from many commonly reported summary statistics, like accuracy. However, random seed is often not included in hyper-parameter optimization, perhaps because the relationship between seed and model quality is hard to describe. This work attempts to describe the relationship between deep net models trained with different random seeds and the behavior of the expected model. We adopt robust hypothesis testing to propose a novel summary statistic for network similarity, referred to as the $\alpha$-trimming level. We use the $\alpha$-trimming level to show that the empirical cumulative distribution function of an ensemble model created from a collection of trained models with different random seeds approximates the average of these functions as the number of models in the collection grows large. This insight provides guidance for how many random seeds should be sampled to ensure that an ensemble of these trained models is a reliable representative. We also show that the $\alpha$-trimming level is more expressive than different performance metrics like validation accuracy, churn, or expected calibration error when taken alone and may help with random seed selection in a more principled fashion. We demonstrate the value of the proposed statistic in real experiments and illustrate the advantage of fine-tuning over random seed with an experiment in transfer learning.

Related papers

• Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness [86.61582747039053]
  Language model training in distributed settings is limited by the communication cost of exchanges. We extend recent work using shared randomness to perform distributed fine-tuning with low bandwidth.
  arXiv  Detail & Related papers  (2023-06-16T17:59:51Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• We need to talk about random seeds [16.33770822558325]
  This opinion piece argues that there are some safe uses for random seeds. An analysis of 85 recent publications from the ACL Anthology finds that more than 50% contain risky uses of random seeds.
  arXiv  Detail & Related papers  (2022-10-24T16:48:45Z)
• Post-Selection Confidence Bounds for Prediction Performance [2.28438857884398]
  In machine learning, the selection of a promising model from a potentially large number of competing models and the assessment of its generalization performance are critical tasks. We propose an algorithm how to compute valid lower confidence bounds for multiple models that have been selected based on their prediction performances in the evaluation set.
  arXiv  Detail & Related papers  (2022-10-24T13:28:43Z)
• Demystifying Randomly Initialized Networks for Evaluating Generative Models [28.8899914083501]
  Evaluation of generative models is mostly based on the comparison between the estimated distribution and the ground truth distribution in a certain feature space. To embed samples into informative features, previous works often use convolutional neural networks optimized for classification. In this paper, we rigorously investigate the feature space of models with random weights in comparison to that of trained models.
  arXiv  Detail & Related papers  (2022-08-19T08:43:53Z)
• Convergence for score-based generative modeling with polynomial complexity [9.953088581242845]
  We prove the first convergence guarantees for the core mechanic behind Score-based generative modeling. Compared to previous works, we do not incur error that grows exponentially in time or that suffers from a curse of dimensionality. We show that a predictor-corrector gives better convergence than using either portion alone.
  arXiv  Detail & Related papers  (2022-06-13T14:57:35Z)
• Distributionally Robust Models with Parametric Likelihood Ratios [123.05074253513935]
  Three simple ideas allow us to train models with DRO using a broader class of parametric likelihood ratios. We find that models trained with the resulting parametric adversaries are consistently more robust to subpopulation shifts when compared to other DRO approaches.
  arXiv  Detail & Related papers  (2022-04-13T12:43:12Z)
• Sampling from Arbitrary Functions via PSD Models [55.41644538483948]
  We take a two-step approach by first modeling the probability distribution and then sampling from that model. We show that these models can approximate a large class of densities concisely using few evaluations, and present a simple algorithm to effectively sample from these models.
  arXiv  Detail & Related papers  (2021-10-20T12:25:22Z)
• Model-based micro-data reinforcement learning: what are the crucial model properties and which model to choose? [0.2836066255205732]
  We contribute to micro-data model-based reinforcement learning (MBRL) by rigorously comparing popular generative models. We find that on an environment that requires multimodal posterior predictives, mixture density nets outperform all other models by a large margin. We also found that deterministic models are on par, in fact they consistently (although non-significantly) outperform their probabilistic counterparts.
  arXiv  Detail & Related papers  (2021-07-24T11:38:25Z)
• Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation [51.091890311312085]
  We propose a new training scheme for auto-regressive sequence generative models, which is effective and stable when operating at large sample space encountered in text generation. Our method stably outperforms Maximum Likelihood Estimation and other state-of-the-art sequence generative models in terms of both quality and diversity.
  arXiv  Detail & Related papers  (2020-07-12T15:31:24Z)
• On the Discrepancy between Density Estimation and Sequence Generation [92.70116082182076]
  log-likelihood is highly correlated with BLEU when we consider models within the same family. We observe no correlation between rankings of models across different families.
  arXiv  Detail & Related papers  (2020-02-17T20:13:35Z)

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.