Continuous-time reinforcement learning tasks commonly use discrete steps of fixed cycle times for actions. As practitioners need to choose the action-cycle time for a given task, a significant concern is whether the hyper-parameters of the learning algorithm need to be re-tuned for each choice of the cycle time, which is prohibitive for real-world robotics. In this work, we investigate the widely-used baseline hyper-parameter values of two policy gradient algorithms -- PPO and SAC -- across different cycle times. Using a benchmark task where the baseline hyper-parameters of both algorithms were shown to work well, we reveal that when a cycle time different than the task default is chosen, PPO with baseline hyper-parameters fails to learn. Moreover, both PPO and SAC with their baseline hyper-parameters perform substantially worse than their tuned values for each cycle time. We propose novel approaches for setting these hyper-parameters based on the cycle time. In our experiments on simulated and real-world robotic tasks, the proposed approaches performed at least as well as the baseline hyper-parameters, with significantly better performance for most choices of the cycle time, and did not result in learning failure for any cycle time. Hyper-parameter tuning still remains a significant barrier for real-world robotics, as our approaches require some initial tuning on a new task, even though it is negligible compared to an extensive tuning for each cycle time. Our approach requires no additional tuning after the cycle time is changed for a given task and is a step toward avoiding extensive and costly hyper-parameter tuning for real-world policy optimization.

A deployed question answering (QA) model can easily fail when the test data has a distribution shift compared to the training data. Robustness tuning (RT) methods have been widely studied to enhance model robustness against distribution shifts before model deployment. However, can we improve a model after deployment? To answer this question, we evaluate test-time adaptation (TTA) to improve a model after deployment. We first introduce COLDQA, a unified evaluation benchmark for robust QA against text corruption and changes in language and domain. We then evaluate previous TTA methods on COLDQA and compare them to RT methods. We also propose a novel TTA method called online imitation learning (OIL). Through extensive experiments, we find that TTA is comparable to RT methods, and applying TTA after RT can significantly boost the performance on COLDQA. Our proposed OIL improves TTA to be more robust to variation in hyper-parameters and test distributions over time.

Check out our latest blogs comprising trends, scope, and predictions of IT society including Anything as a Service (XaaS), IoTs, Next-Gen ERP, AI, Augmented Virtual Reality, Cryptocurrency, and their integration with other high-end technologies like natural language, deep & machine learning and robotics. Here, we discuss disruptive digital marketing technologies followed by CRM, customer analytics, consumer behavior, and HR. Our blogs will help you comprehend the cross-connections and comparisons of different tools and software technologies with their impact over each other on various platforms and industries.

It is now well understood that machine learning models, trained on data without due care, often exhibit unfair and discriminatory behavior against certain populations. Traditional algorithmic fairness research has mainly focused on supervised learning tasks, particularly classification. While fairness in unsupervised learning has received some attention, the literature has primarily addressed fair representation learning of continuous embeddings. In this paper, we conversely focus on unsupervised learning using probabilistic graphical models with discrete latent variables. We develop a fair stochastic variational inference technique for the discrete latent variables, which is accomplished by including a fairness penalty on the variational distribution that aims to respect the principles of intersectionality, a critical lens on fairness from the legal, social science, and humanities literature, and then optimizing the variational parameters under this penalty. We first show the utility of our method in improving equity and fairness for clustering using na\"ive Bayes and Gaussian mixture models on benchmark datasets. To demonstrate the generality of our approach and its potential for real-world impact, we then develop a special-purpose graphical model for criminal justice risk assessments, and use our fairness approach to prevent the inferences from encoding unfair societal biases.

We describe a light-weight yet performant system for hyper-parameter optimization that approximately minimizes an overall scalar cost function that is obtained by combining multiple performance objectives using a target-priority-limit scalarizer. It also supports a trade-off mode, where the goal is to find an appropriate trade-off among objectives by interacting with the user. We focus on the common scenario where there are on the order of tens of hyper-parameters, each with various attributes such as a range of continuous values, or a finite list of values, and whether it should be treated on a linear or logarithmic scale. The system supports multiple asynchronous simulations and is robust to simulation stragglers and failures. While the algorithm we describe will work in principle for any value of n, our focus is on the case where n is modest (e.g., < 10). Each of these objectives has a sense, which means that we either want the objective to be large (i.e., to maximize it) or small (i.e., to minimize it).

Although the principle is straightforward, this method is still error-prone. Here is a list of the most common mistakes I have encountered. This error I've seen it happen quite a few times. Students define a grid on a parameter, run GridSearchCV, extract the hyper-parameter value corresponding to the best score, and …. that's it! Depending on how well the grid was defined, just looking at the best score and its corresponding hyper-parameter value might not be enough to draw the right conclusions.

They are set before training starts, either by intuition or a hyper-parameter search. They either stay static or change based on a pre-determined schedule. We are introducing dynamic hyper-parameters which can be manually adjusted during the training based on model training stats. Hyper-parameters are parameters that control the learning process of models, such as the learning rate, batch size, and weight decay. The model might not learn if the hyper-parameters are not set correctly.

The most successful methods such as ReLU transfer functions, batch normalization, Xavier initialization, dropout, learning rate decay, or dynamic optimizers, have become standards in the field due, particularly, to their ability to increase the performance of Neural Networks (NNs) significantly and in almost all situations. Here we present a new method to calculate the gradients while training NNs, and show that it significantly improves final performance across architectures, data-sets, hyper-parameter values, training length, and model sizes, including when it is being combined with other common performance-improving methods (such as the ones mentioned above). Besides being effective in the wide array situations that we have tested, the increase in performance (e.g. F1) it provides is as high or higher than this one of all the other widespread performance-improving methods that we have compared against. We call our method Population Gradients (PG), and it consists on using a population of NNs to calculate a non-local estimation of the gradient, which is closer to the theoretical exact gradient (i.e. this one obtainable only with an infinitely big data-set) of the error function than the empirical gradient (i.e. this one obtained with the real finite data-set).