Transformer models classify random numbers

• URL: http://arxiv.org/abs/2405.03904v1
• Date: Mon, 6 May 2024 23:36:03 GMT
• Title: Transformer models classify random numbers
• Authors: Rishabh Goel, YiZi Xiao, Ramin Ramezani,
• Abstract summary: We present a deep learning model that encodes some of the tests from the NIST Statistical Test Suite (STS) in a single model that also runs much faster. This model performs multi-label classification on these tests and outputs the probability of passing each statistical test that it encodes. We achieve a high degree of accuracy with a sample f1 score of above 0.9.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Random numbers are incredibly important in a variety of fields, and the need for their validation remains important. A Quantum Random Number Generator (QRNG) can theoretically generate truly random numbers however this does not remove the need to thoroughly test their randomness. Generally, the task of validating random numbers has been delegated to different statistical tests such as the tests from the NIST Statistical Test Suite (STS) which are often slow and only perform one task at a time. Our work presents a deep learning model that utilizes the transformer architecture to encode some of the tests from the NIST STS in a single model that also runs much faster. This model performs multi-label classification on these tests and outputs the probability of passing each statistical test that it encodes. We perform a thorough hyper-parameter optimization to converge on the best possible model and as a result, achieve a high degree of accuracy with a sample f1 score of above 0.9.

Related papers

• Statistical Quality and Reproducibility of Pseudorandom Number Generators in Machine Learning technologies [0.0]
  We compare the statistical quality of PRNGs used in ML frameworks against their original C implementations.<n>Our findings challenge claims of statistical robustness, revealing that even generators labeled ''crush-resistant'' (e.g., PCG, Philox) may fail certain statistical tests.
  arXiv  Detail & Related papers  (2025-07-02T09:38:00Z)
• Sample, Don't Search: Rethinking Test-Time Alignment for Language Models [55.2480439325792]
  We introduce QAlign, a new test-time alignment approach. As we scale test-time compute, QAlign converges to sampling from the optimal aligned distribution for each individual prompt. By adopting recent advances in Markov chain Monte Carlo for text generation, our method enables better-aligned outputs without modifying the underlying model or even requiring logit access.
  arXiv  Detail & Related papers  (2025-04-04T00:41:40Z)
• On Using Quasirandom Sequences in Machine Learning for Model Weight Initialization [0.0]
  We investigate whether substituting PRNGs for low-discrepancy quasirandom number generators (QRNGs) as a source of randomness for initializers can improve model performance. Our findings indicate that QRNG-based neural network initializers either reach a higher accuracy or achieve the same accuracy more quickly than PRNG-based initializers.
  arXiv  Detail & Related papers  (2024-08-05T17:33:09Z)
• Statistical testing of random number generators and their improvement using randomness extraction [0.0]
  We present and make available a comprehensive statistical testing environment (STE) based on existing statistical test suites. The STE can be parameterised to run lightweight (i.e. fast) all the way to intensive testing, which goes far beyond what is required by certification bodies. We then present and implement a variety of post-processing methods, in the form of randomness extractors, which improve the RNG's output quality under different sets of assumptions.
  arXiv  Detail & Related papers  (2024-03-27T16:05:02Z)
• A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks [65.34977803841007]
  Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. We show how by simply changing the temporal scheduling of the update rule for the synaptic weights leads to an algorithm that is much more efficient and stable than the original one.
  arXiv  Detail & Related papers  (2022-11-16T00:11:04Z)
• Validation tests of GBS quantum computers give evidence for quantum advantage with a decoherent target [62.997667081978825]
  We use positive-P phase-space simulations of grouped count probabilities as a fingerprint for verifying multi-mode data. We show how one can disprove faked data, and apply this to a classical count algorithm.
  arXiv  Detail & Related papers  (2022-11-07T12:00:45Z)
• Near-optimal multiple testing in Bayesian linear models with finite-sample FDR control [11.011242089340438]
  In high dimensional variable selection problems, statisticians often seek to design multiple testing procedures that control the False Discovery Rate (FDR) We introduce Model-X procedures that provably control the frequentist FDR from finite samples, even when the model is misspecified. Our proposed procedure, PoEdCe, incorporates three key ingredients: Posterior Expectation, distilled randomization test (dCRT), and the Benjamini-Hochberg procedure with e-values.
  arXiv  Detail & Related papers  (2022-11-04T22:56:41Z)
• Learning to Increase the Power of Conditional Randomization Tests [8.883733362171032]
  The model-X conditional randomization test is a generic framework for conditional independence testing. We introduce novel model-fitting schemes that are designed to explicitly improve the power of model-X tests.
  arXiv  Detail & Related papers  (2022-07-03T12:29:25Z)
• Quantifying Inherent Randomness in Machine Learning Algorithms [7.591218883378448]
  This paper uses an empirical study to examine the effects of randomness in model training and randomness in the partitioning of a dataset into training and test subsets. We quantify and compare the magnitude of the variation in predictive performance for the following ML algorithms: Random Forests (RFs), Gradient Boosting Machines (GBMs), and Feedforward Neural Networks (FFNNs)
  arXiv  Detail & Related papers  (2022-06-24T15:49:52Z)
• TTAPS: Test-Time Adaption by Aligning Prototypes using Self-Supervision [70.05605071885914]
  We propose a novel modification of the self-supervised training algorithm SwAV that adds the ability to adapt to single test samples. We show the success of our method on the common benchmark dataset CIFAR10-C.
  arXiv  Detail & Related papers  (2022-05-18T05:43:06Z)
• Efficient Test-Time Model Adaptation without Forgetting [60.36499845014649]
  Test-time adaptation seeks to tackle potential distribution shifts between training and testing data. We propose an active sample selection criterion to identify reliable and non-redundant samples. We also introduce a Fisher regularizer to constrain important model parameters from drastic changes.
  arXiv  Detail & Related papers  (2022-04-06T06:39:40Z)
• MEMO: Test Time Robustness via Adaptation and Augmentation [131.28104376280197]
  We study the problem of test time robustification, i.e., using the test input to improve model robustness. Recent prior works have proposed methods for test time adaptation, however, they each introduce additional assumptions. We propose a simple approach that can be used in any test setting where the model is probabilistic and adaptable.
  arXiv  Detail & Related papers  (2021-10-18T17:55:11Z)
• ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms [58.684954492439424]
  We propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data. The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN)
  arXiv  Detail & Related papers  (2021-04-11T12:14:04Z)

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.