Frequency Principle google
Previous studies have shown that deep neural networks (DNNs) with common settings often capture target functions from low to high frequency, which is called Frequency Principle (F-Principle). It has also been shown that F-Principle can provide an understanding to the often observed good generalization ability of DNNs. …

AutoTune google
Big data analytics frameworks (BDAFs) have been widely used for data processing applications. These frameworks provide a large number of configuration parameters to users, which leads to a tuning issue that overwhelms users. To address this issue, many automatic tuning approaches have been proposed. However, it remains a critical challenge to generate enough samples in a high-dimensional parameter space within a time constraint. In this paper, we present AutoTune–an automatic parameter tuning system that aims to optimize application execution time on BDAFs. AutoTune first constructs a smaller-scale testbed from the production system so that it can generate more samples, and thus train a better prediction model, under a given time constraint. Furthermore, the AutoTune algorithm produces a set of samples that can provide a wide coverage over the high-dimensional parameter space, and searches for more promising configurations using the trained prediction model. AutoTune is implemented and evaluated using the Spark framework and HiBench benchmark deployed on a public cloud. Extensive experimental results illustrate that AutoTune improves on default configurations by 63.70% on average, and on the five state-of-the-art tuning algorithms by 6%-23%. …

LanguagE-Action Reward Network (LEARN) google
Recent reinforcement learning (RL) approaches have shown strong performance in complex domains such as Atari games, but are often highly sample inefficient. A common approach to reduce interaction time with the environment is to use reward shaping, which involves carefully designing reward functions that provide the agent intermediate rewards for progress towards the goal. However, designing appropriate shaping rewards is known to be difficult as well as time-consuming. In this work, we address this problem by using natural language instructions to perform reward shaping. We propose the LanguagE-Action Reward Network (LEARN), a framework that maps free-form natural language instructions to intermediate rewards based on actions taken by the agent. These intermediate language-based rewards can seamlessly be integrated into any standard reinforcement learning algorithm. We experiment with Montezuma’s Revenge from the Atari Learning Environment, a popular benchmark in RL. Our experiments on a diverse set of 15 tasks demonstrate that, for the same number of interactions with the environment, language-based rewards lead to successful completion of the task 60% more often on average, compared to learning without language. …

BFGAN google
In many natural language generation tasks, incorporating additional knowledge like lexical constraints into the model’s output is significant, which take the form of phrases or words that must be present in the output sequence. Unfortunately, existing neural language model cannot be used directly to generate lexically constrained sentences. In this paper, we propose a new algorithmic framework called BFGAN to address this challenge. We employ a backward generator and a forward generator to generate lexically constrained sentence together, and use a discriminator to guide the joint training of two generators by assigning them reward signals. Experimental results on automatic and human evaluation demonstrate significant improvements over previous baselines. …