Precise Model Benchmarking with Only a Few Observations

• URL: http://arxiv.org/abs/2410.05222v1
• Date: Mon, 7 Oct 2024 17:26:31 GMT
• Title: Precise Model Benchmarking with Only a Few Observations
• Authors: Riccardo Fogliato, Pratik Patil, Nil-Jana Akpinar, Mathew Monfort,
• Abstract summary: We propose an empirical Bayes (EB) estimator that balances direct and regression estimates for each subgroup separately. EB consistently provides more precise estimates of the LLM performance compared to the direct and regression approaches.
• Score: 6.092112060364272
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: How can we precisely estimate a large language model's (LLM) accuracy on questions belonging to a specific topic within a larger question-answering dataset? The standard direct estimator, which averages the model's accuracy on the questions in each subgroup, may exhibit high variance for subgroups (topics) with small sample sizes. Synthetic regression modeling, which leverages the model's accuracy on questions about other topics, may yield biased estimates that are too unreliable for large subgroups. We prescribe a simple yet effective solution: an empirical Bayes (EB) estimator that balances direct and regression estimates for each subgroup separately, improving the precision of subgroup-level estimates of model performance. Our experiments on multiple datasets show that this approach consistently provides more precise estimates of the LLM performance compared to the direct and regression approaches, achieving substantial reductions in the mean squared error. Confidence intervals for EB estimates also have near-nominal coverage and are narrower compared to those for the direct estimator. Additional experiments on tabular and vision data validate the benefits of this EB approach.

Related papers

• Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference [5.924780594614676]
  We show that the error of estimating a single coordinate can be enlarged by a multiple of $sqrtd$ when data are allowed to be arbitrarily adaptive. We propose a novel estimator for single coordinate inference via solving a Two-stage Adaptive Linear Estimating equation (TALE)
  arXiv  Detail & Related papers  (2023-10-01T00:45:09Z)
• Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play [16.262574174989698]
  Introspective Self-play (ISP) is a simple approach to improve the uncertainty estimation of a deep neural network under dataset bias. We show that ISP provably improves the bias-awareness of the model representation and the resulting uncertainty estimates.
  arXiv  Detail & Related papers  (2023-02-11T22:59:08Z)
• Training Experimentally Robust and Interpretable Binarized Regression Models Using Mixed-Integer Programming [3.179831861897336]
  We present a model-based approach to training robust and interpretable binarized regression models for multiclass classification tasks. Our MIP model balances the optimization of prediction margin and model size by using a weighted objective. We show the effectiveness of training robust and interpretable binarized regression models using MIP.
  arXiv  Detail & Related papers  (2021-12-01T11:53:08Z)
• Expected Validation Performance and Estimation of a Random Variable's Maximum [48.83713377993604]
  We analyze three statistical estimators for expected validation performance. We find the unbiased estimator has the highest variance, and the estimator with the smallest variance has the largest bias. We find that the two biased estimators lead to the fewest incorrect conclusions.
  arXiv  Detail & Related papers  (2021-10-01T18:48:47Z)
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality [106.50867011164584]
  We show that we can compute the exact Bayes error of generative models learned using normalizing flows. We use our approach to conduct a thorough investigation of state-of-the-art classification models.
  arXiv  Detail & Related papers  (2021-06-07T06:21:20Z)
• Model-based metrics: Sample-efficient estimates of predictive model subpopulation performance [11.994417027132807]
  Machine learning models $-$ now commonly developed to screen, diagnose, or predict health conditions are evaluated with a variety of performance metrics. Subpopulation performance metrics are typically computed using only data from that subgroup, resulting in higher variance estimates for smaller groups. We propose using an evaluation model $-$ a model that describes the conditional distribution of the predictive model score $-$ to form model-based metric (MBM) estimates.
  arXiv  Detail & Related papers  (2021-04-25T19:06:34Z)
• Flexible Model Aggregation for Quantile Regression [92.63075261170302]
  Quantile regression is a fundamental problem in statistical learning motivated by a need to quantify uncertainty in predictions. We investigate methods for aggregating any number of conditional quantile models. All of the models we consider in this paper can be fit using modern deep learning toolkits.
  arXiv  Detail & Related papers  (2021-02-26T23:21:16Z)
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations [98.3066727301239]
  We identify two key properties of the training data that drive this behavior. We show how the inductive bias of models towards "memorizing" fewer examples can cause over parameterization to hurt.
  arXiv  Detail & Related papers  (2020-05-09T01:59:13Z)
• SUMO: Unbiased Estimation of Log Marginal Probability for Latent Variable Models [80.22609163316459]
  We introduce an unbiased estimator of the log marginal likelihood and its gradients for latent variable models based on randomized truncation of infinite series. We show that models trained using our estimator give better test-set likelihoods than a standard importance-sampling based approach for the same average computational cost.
  arXiv  Detail & Related papers  (2020-04-01T11:49:30Z)
• Meta-Learned Confidence for Few-shot Learning [60.6086305523402]
  A popular transductive inference technique for few-shot metric-based approaches, is to update the prototype of each class with the mean of the most confident query examples. We propose to meta-learn the confidence for each query sample, to assign optimal weights to unlabeled queries. We validate our few-shot learning model with meta-learned confidence on four benchmark datasets.
  arXiv  Detail & Related papers  (2020-02-27T10:22:17Z)

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.