arXiv subjects

Yuu Jinnai

Publications and source records attributed to Yuu Jinnai.

29 records · Page 2Linked to original sources

arXiv2024

Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding

One of the most important challenges in text generation systems is to produce outputs that are not only correct but also diverse. Recently, Minimum Bayes-Risk (MBR) decoding has gained prominence for generating sentences of the highest quality among the decoding algorithms. However, existing algorithms proposed for generating diverse outputs are predominantly based on beam search or random sampling, thus their output quality is capped by these underlying methods. In this paper, we investigate an alternative approach -- we develop diversity-promoting decoding algorithms by enforcing diversity objectives to MBR decoding. We propose two variants of MBR, Diverse MBR (DMBR) and $k$-medoids MBR (KMBR), methods to generate a set of sentences with high quality and diversity. We evaluate DMBR and KMBR on a variety of directed text generation tasks using encoder-decoder models and a large language model with prompting. The experimental results show that the proposed method achieves a better trade-off than the diverse beam search and sampling algorithms.

cs.CL↗

arXiv2024

On the True Distribution Approximation of Minimum Bayes-Risk Decoding

Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in text generation. MBR decoding considers texts sampled from a model as pseudo-references and selects the text with the highest similarity to the others. Therefore, sampling is one of the key elements of MBR decoding, and previous studies reported that the performance varies by sampling methods. From a theoretical standpoint, this performance variation is likely tied to how closely the samples approximate the true distribution of references. However, this approximation has not been the subject of in-depth study. In this study, we propose using anomaly detection to measure the degree of approximation. We first closely examine the performance variation and then show that previous hypotheses about samples do not correlate well with the variation, but our introduced anomaly scores do. The results are the first to empirically support the link between the performance and the core assumption of MBR decoding.

cs.CL↗

arXiv2023

On the Depth between Beam Search and Exhaustive Search for Text Generation

Beam search and exhaustive search are two extreme ends of text decoding algorithms with respect to the search depth. Beam search is limited in both search width and depth, whereas exhaustive search is a global search that has no such limitations. Surprisingly, beam search is not only computationally cheaper but also performs better than exhaustive search despite its higher search error. Plenty of research has investigated a range of beam widths, from small to large, and reported that a beam width that is neither too large nor too small is desirable. However, in terms of search depth, only the two extreme ends, beam search and exhaustive search are studied intensively. In this paper, we examine a range of search depths between the two extremes to discover the desirable search depth. To this end, we introduce Lookahead Beam Search (LBS), a multi-step lookahead search that optimizes the objective considering a fixed number of future steps. Beam search and exhaustive search are special cases of LBS where the lookahead depth is set to $0$ and $\infty$, respectively. We empirically evaluate the performance of LBS and find that it outperforms beam search overall on machine translation tasks. The result suggests there is room for improvement in beam search by searching deeper. Inspired by the analysis, we propose Lookbehind Heuristic Beam Search, a computationally feasible search algorithm that heuristically simulates LBS with 1-step lookahead. The empirical results show that the proposed method outperforms vanilla beam search on machine translation and text summarization tasks.

cs.CL↗

arXiv2023

Blind Signal Separation for Fast Ultrasound Computed Tomography

Breast cancer is the most prevalent cancer with a high mortality rate in women over the age of 40. Many studies have shown that the detection of cancer at earlier stages significantly reduces patients' mortality and morbidity rages. Ultrasound computer tomography (USCT) is considered as a promising screening tool for diagnosing early-stage breast cancer as it is cost-effective and produces 3D images without radiation exposure. However, USCT is not a popular choice mainly due to its prolonged imaging time. USCT is time-consuming because it needs to transmit a number of ultrasound waves and record them one by one to acquire a high-quality image. We propose FastUSCT, a method to acquire a high-quality image faster than traditional methods for USCT. FastUSCT consists of three steps. First, it transmits multiple ultrasound waves at the same time to reduce the imaging time. Second, it separates the overlapping waves recorded by the receiving elements into each wave with UNet. Finally, it reconstructs an ultrasound image with a synthetic aperture method using the separated waves. We evaluated FastUSCT on simulation on breast digital phantoms. We trained the UNet on simulation using natural images and transferred the model for the breast digital phantoms. The empirical result shows that FastUSCT significantly improves the quality of the image under the same imaging time to the conventional USCT method, especially when the imaging time is limited.

eess.IV↗

arXiv2021

Lipschitz Lifelong Reinforcement Learning

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes (MDPs) and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate the benefits of the method in Lifelong RL experiments.

cs.LG↗

arXiv2019

Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search

Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this paper, we present a novel scalable Monte Carlo Tree Search (MCTS) based NAS agent, named AlphaX, to tackle these two aspects. AlphaX improves the search efficiency by adaptively balancing the exploration and exploitation at the state level, and by a Meta-Deep Neural Network (DNN) to predict network accuracies for biasing the search toward a promising region. To amortize the network evaluation cost, AlphaX accelerates MCTS rollouts with a distributed design and reduces the number of epochs in evaluating a network by transfer learning, which is guided with the tree structure in MCTS. In 12 GPU days and 1000 samples, AlphaX found an architecture that reaches 97.84\% top-1 accuracy on CIFAR-10, and 75.5\% top-1 accuracy on ImageNet, exceeding SOTA NAS methods in both the accuracy and sampling efficiency. Particularly, we also evaluate AlphaX on NASBench-101, a large scale NAS dataset; AlphaX is 3x and 2.8x more sample efficient than Random Search and Regularized Evolution in finding the global optimum. Finally, we show the searched architecture improves a variety of vision applications from Neural Style Transfer, to Image Captioning and Object Detection.

cs.LG↗

arXiv2019

AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search

Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this paper, we present a novel scalable Monte Carlo Tree Search (MCTS) based NAS agent, named AlphaX, to tackle these two aspects. AlphaX improves the search efficiency by adaptively balancing the exploration and exploitation at the state level, and by a Meta-Deep Neural Network (DNN) to predict network accuracies for biasing the search toward a promising region. To amortize the network evaluation cost, AlphaX accelerates MCTS rollouts with a distributed design and reduces the number of epochs in evaluating a network by transfer learning guided with the tree structure in MCTS. In 12 GPU days and 1000 samples, AlphaX found an architecture that reaches 97.84\% top-1 accuracy on CIFAR-10, and 75.5\% top-1 accuracy on ImageNet, exceeding SOTA NAS methods in both the accuracy and sampling efficiency. Particularly, we also evaluate AlphaX on NASBench-101, a large scale NAS dataset; AlphaX is 3x and 2.8x more sample efficient than Random Search and Regularized Evolution in finding the global optimum. Finally, we show the searched architecture improves a variety of vision applications from Neural Style Transfer, to Image Captioning and Object Detection.

cs.CV↗

arXiv2019

Finding Options that Minimize Planning Time

We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes. We first show that the problem is NP-hard, even if the task is constrained to be deterministic---the first such complexity result for option discovery. We then present the first polynomial-time boundedly suboptimal approximation algorithm for this setting, and empirically evaluate it against both the optimal options and a representative collection of heuristic approaches in simple grid-based domains including the classic four-rooms problem.

cs.AI↗

arXiv2019

Discovering Options for Exploration by Minimizing Cover Time

One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. The proposed algorithm finds an option which provably diminishes the expected number of steps to visit every state in the state space by a uniform random walk. We show empirically that the proposed algorithm improves the learning time in several domains with sparse rewards.

cs.AI↗

arXiv2017

On Hash-Based Work Distribution Methods for Parallel Best-First Search

Parallel best-first search algorithms such as Hash Distributed A* (HDA*) distribute work among the processes using a global hash function. We analyze the search and communication overheads of state-of-the-art hash-based parallel best-first search algorithms, and show that although Zobrist hashing, the standard hash function used by HDA*, achieves good load balance for many domains, it incurs significant communication overhead since almost all generated nodes are transferred to a different processor than their parents. We propose Abstract Zobrist hashing, a new work distribution method for parallel search which, instead of computing a hash value based on the raw features of a state, uses a feature projection function to generate a set of abstract features which results in a higher locality, resulting in reduced communications overhead. We show that Abstract Zobrist hashing outperforms previous methods on search domains using hand-coded, domain specific feature projection functions. We then propose GRAZHDA*, a graph-partitioning based approach to automatically generating feature projection functions. GRAZHDA* seeks to approximate the partitioning of the actual search space graph by partitioning the domain transition graph, an abstraction of the state space graph. We show that GRAZHDA* outperforms previous methods on domain-independent planning.

cs.AI↗

arXiv2017

A Survey of Parallel A*

A* is a best-first search algorithm for finding optimal-cost paths in graphs. A* benefits significantly from parallelism because in many applications, A* is limited by memory usage, so distributed memory implementations of A* that use all of the aggregate memory on the cluster enable problems that can not be solved by serial, single-machine implementations to be solved. We survey approaches to parallel A*, focusing on decentralized approaches to A* which partition the state space among processors. We also survey approaches to parallel, limited-memory variants of A* such as parallel IDA*.

cs.AI↗