ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables

• URL: http://arxiv.org/abs/2105.14141v1
• Date: Fri, 28 May 2021 23:19:54 GMT
• Title: ARMS: Antithetic-REINFORCE-Multi-Sample Gradient for Binary Variables
• Authors: Alek Dimitriev and Mingyuan Zhou
• Abstract summary: Antithetic REINFORCE-based Multi-Sample gradient estimator. ARMS uses a copula to generate any number of mutually antithetic samples. We evaluate ARMS on several datasets for training generative models, and our experimental results show that it outperforms competing methods.
• Score: 60.799183326613395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Estimating the gradients for binary variables is a task that arises frequently in various domains, such as training discrete latent variable models. What has been commonly used is a REINFORCE based Monte Carlo estimation method that uses either independent samples or pairs of negatively correlated samples. To better utilize more than two samples, we propose ARMS, an Antithetic REINFORCE-based Multi-Sample gradient estimator. ARMS uses a copula to generate any number of mutually antithetic samples. It is unbiased, has low variance, and generalizes both DisARM, which we show to be ARMS with two samples, and the leave-one-out REINFORCE (LOORF) estimator, which is ARMS with uncorrelated samples. We evaluate ARMS on several datasets for training generative models, and our experimental results show that it outperforms competing methods. We also develop a version of ARMS for optimizing the multi-sample variational bound, and show that it outperforms both VIMCO and DisARM. The code is publicly available.

Related papers

• Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score [62.54911162109439]
  Adversarial detection aims to determine whether a given sample is an adversarial one based on the discrepancy between natural and adversarial distributions. We propose a new statistic called expected perturbation score (EPS), which is essentially the expected score of a sample after various perturbations. We develop EPS-based maximum mean discrepancy (MMD) as a metric to measure the discrepancy between the test sample and natural samples.
  arXiv  Detail & Related papers  (2023-05-25T13:14:58Z)
• Variable Selection for Kernel Two-Sample Tests [10.768155884359777]
  We propose a framework based on the kernel maximum mean discrepancy (MMD) We present mixed-integer programming formulations and develop exact and approximation algorithms with performance guarantees. Experiment results on synthetic and real datasets demonstrate the superior performance of our approach.
  arXiv  Detail & Related papers  (2023-02-15T00:39:56Z)
• Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition [62.83832841523525]
  We propose a fast and accurate parallel transformer, termed Paraformer. It accurately predicts the number of output tokens and extract hidden variables. It can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.
  arXiv  Detail & Related papers  (2022-06-16T17:24:14Z)
• Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization [50.725191156128645]
  Multi-armed bandit algorithms like Thompson Sampling can be used to conduct adaptive experiments. We present simulations for 2-arm experiments that explore two algorithms that combine the benefits of uniform randomization for statistical analysis.
  arXiv  Detail & Related papers  (2021-12-15T22:11:58Z)
• CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator [60.799183326613395]
  We propose an unbiased estimator for categorical random variables based on multiple mutually negatively correlated (jointly antithetic) samples. CARMS combines REINFORCE with copula based sampling to avoid duplicate samples and reduce its variance, while keeping the estimator unbiased using importance sampling. We evaluate CARMS on several benchmark datasets on a generative modeling task, as well as a structured output prediction task, and find it to outperform competing methods including a strong self-control baseline.
  arXiv  Detail & Related papers  (2021-10-26T20:14:30Z)
• Autoregressive Score Matching [113.4502004812927]
  We propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariable log-conditionals (scores) For AR-CSM models, this divergence between data and model distributions can be computed and optimized efficiently, requiring no expensive sampling or adversarial training. We show with extensive experimental results that it can be applied to density estimation on synthetic data, image generation, image denoising, and training latent variable models with implicit encoders.
  arXiv  Detail & Related papers  (2020-10-24T07:01:24Z)
• DisARM: An Antithetic Gradient Estimator for Binary Latent Variables [35.473848208376886]
  We introduce the Augment-REINFORCE-Merge (ARM) estimator for training models with binary latent variables. We show that ARM can be improved by analytically integrating out the randomness introduced by the augmentation process. Our estimator, DisARM, is simple to implement and has the same computational cost as ARM.
  arXiv  Detail & Related papers  (2020-06-18T17:09:35Z)
• Deep Synthetic Minority Over-Sampling Technique [3.3707422585608953]
  We adapt the SMOTE idea in deep learning architecture. Deep SMOTE can outperform traditional SMOTE in terms of precision, F1 score and Area Under Curve (AUC) in majority of test cases.
  arXiv  Detail & Related papers  (2020-03-22T02:44:46Z)
• Predictive Sampling with Forecasting Autoregressive Models [13.021014899410684]
  Autoregressive models (ARMs) currently hold state-of-the-art performance in likelihood-based modeling of image and audio data. We introduce the predictive sampling algorithm: a procedure that exploits the fast inference property of ARMs in order to speed up sampling, while keeping the model intact.
  arXiv  Detail & Related papers  (2020-02-23T15:58:47Z)

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.