Task-adapted compressed sensing magnetic resonance imaging (CS-MRI) is emerging to address the specific demands of downstream clinical tasks with significantly fewer k-space measurements than required by Nyquist sampling. However, existing task-adapted CS-MRI methods suffer from the uncertainty problem for medical diagnosis and cannot achieve adaptive sampling in end-to-end optimization with reconstruction or clinical tasks. To address these limitations, we propose the first task-adapted CS-MRI from the information-theoretic perspective to simultaneously achieve probabilistic inference for uncertainty prediction and adapt to arbitrary sampling ratios and versatile clinical applications. Specifically, we formalize the task-adapted CS-MRI optimization problem by maximizing the mutual information between undersampled k-space measurements and clinical tasks to enable probabilistic inference for addressing the uncertainty problem. We leverage amortized optimization and construct tractable variational bounds for mutual information to jointly optimize sampling, reconstruction, and task-inference models, which enables flexible sampling ratio control using a single end-to-end trained model. Furthermore, the proposed framework addresses two kinds of distinct clinical scenarios within a unified approach, i.e., i) joint task and reconstruction, where reconstruction serves as an auxiliary process to enhance task performance; and ii) task implementation with suppressed reconstruction, applicable for privacy protection. Extensive experiments on large-scale MRI datasets demonstrate that the proposed framework achieves highly competitive performance on standard metrics like Dice compared to deterministic counterpart but provides better distribution matching to the ground-truth posterior distribution as measured by the generalized energy distance (GED).

Coarse-Grained Reconfigurable Architectures (CGRAs) have emerged as promising solutions for energyefficient computing in edge devices and datacenter accelerators. While offering substantial performance benefits, their adoption is hindered by the NP-hard loop mapping problem during compilation. In this paper, we present NaviMap, a neuralsymbolic framework combining partial order-aware graph embeddings with deep reinforcement learning. Experimental results demonstrate that NaviMap achieves a$1.95 \times$speedup in solving CGRA mapping problems compared with state-of-the-art methods, while producing mappings with equivalent or superior performance.

We propose Noise Conditional Variational Score Distillation (NCVSD), a novel method for distilling pretrained diffusion models into generative denoisers. We achieve this by revealing that the unconditional score function implicitly characterizes the score function of denoising posterior distributions. By integrating this insight into the Variational Score Distillation (VSD) framework, we enable scalable learning of generative denoisers capable of approximating samples from the denoising posterior distribution across a wide range of noise levels. The proposed generative denoisers exhibit desirable properties that allow fast generation while preserve the benefit of iterative refinement: (1) fast one-step generation through sampling from pure Gaussian noise at high noise levels; (2) improved sample quality by scaling the test-time compute with multi-step sampling; and (3) zero-shot probabilistic inference for flexible and controllable sampling. We evaluate NCVSD through extensive experiments, including class-conditional image generation and inverse problem solving. By scaling the test-time compute, our method outperforms teacher diffusion models and is on par with consistency models of larger sizes. Additionally, with significantly fewer NFEs than diffusion-based methods, we achieve record-breaking LPIPS on inverse problems.

Fourier phase retrieval (FPR) is a longstanding ill-posed non-convex inverse problem suffering from failure in reconstruction. Existing methods usually mitigate the issue in a trial-and-error fashion and cannot identify the failure to flexibly adjust the FPR process. In this paper, we propose FA-FPR, a novel failure aware method that guides FPR with diffusion priors by failure detection. We first discover that unsuccessful reconstructions can be identified as fake images due to their distinct structures from true signals, and then leverage a plug-and-play fake image detector to automatically determine the approximation to true signals. Furthermore, we develop a hybrid decoupling scheme that adaptively combines Gaussian noise and predicted noise by score function based on the failure detection. Extensive experiments under various oversampling ratios with noisy and noiseless measurements demonstrate that FA-FPR requires less than 50% number of repeated experiments on average to achieve the state-of-the-art performance.

Existing diffusion models for inverse problems have demonstrated impressive performance but suffer from prohibitive sampling complexity due to lengthy iterative sampling procedures. While introducing pre-trained consistency models (CMs) as priors holds promise for fast and high-quality sampling, theoretical disparities between CMs and diffusion models remain, hindering the application of CMs in solving inverse problems. To address this issue, we propose a novel framework, named Dual Data Consistency Guided Consistency Model (DCCM), that for the first time to solve inverse problems with pretrained CM priors. We establish a denoising interpretation of CMs to set up the equivalence between CMs and denoisers and incorporate CM in a theoretically sound fashion. Consequently, we develop refined data consistency to facilitate optimization with CM priors and avoid local minima caused by the nonlinearity of degradation operators. Furthermore, we introduce the data consistency shortcut that leverages the manifold hypothesis to approximate refined data consistency and bypass backpropagation for enhanced sampling speed without reconstruction quality loss. Extensive experiments demonstrate DCCM achieves state-of-the-art performance in terms of reconstruction quality and sampling speed in a wide range tasks of image deblurring, super-resolution, and inpainting.

Recent diffusion models provide a promising zero-shot solution to noisy linear inverse problems without retraining for specific inverse problems. In this paper, we reveal that recent methods can be uniformly interpreted as employing a Gaussian approximation with hand-crafted isotropic covariance for the intractable denoising posterior to approximate the conditional posterior mean. Inspired by this finding, we propose to improve recent methods by using more principled covariance determined by maximum likelihood estimation. To achieve posterior covariance optimization without retraining, we provide general plug-and-play solutions based on two approaches specifically designed for leveraging pre-trained models with and without reverse covariance. We further propose a scalable method for learning posterior covariance prediction based on representation with orthonormal basis. Experimental results demonstrate that the proposed methods significantly enhance reconstruction performance without requiring hyperparameter tuning.

Multitask learning has led to great success in many deep learning applications during the last decade. However, recent experiments have demonstrated that the performance of multitask learning depends on how to balance the relationship between different tasks. Therefore, many approaches have been proposed to adjust per-task gradient directions or design a more appropriate task reweighting scheme based on task-level statistics. In this article, we discuss how to boost the performance of multitask learning by using more fine-grained sample gradient information. To this end, we propose the concept of sample gradient similarity, which measures the agreement between the sample gradient for a task and the true gradient. Based on this concept, greater weight is assigned to more consistent tasks and more robust training samples to improve the training process of multitask learning. Extensive experimental results show that our proposed method outperforms the state-of-the-art algorithms on a series of challenging multitask datasets.

Improving the generalization performance of deep neural networks (DNNs) trained by minibatch stochastic gradient descent (SGD) has raised lots of concerns from deep learning practitioners. The standard simple random sampling (SRS) scheme used in minibatch SGD treats all training samples equally in gradient estimation. In this article, we study a new data selection method based on the intrinsic property of the training set to help DNNs have better generalization performance. Our theoretical analysis suggests that this new sampling scheme, called the nontypicality sampling scheme, boosts the generalization performance of DNNs through biasing the solution toward wider minima, under certain assumptions. We confirm our findings experimentally and show that more variants of minibatch SGD can also benefit from the new sampling scheme. Finally, we discuss an extension of the nontypicality sampling scheme that holds promise to enhance both generalization performance and convergence speed of minibatch SGD.

Deep learning has become the most powerful machine learning tool in the last decade. However, how to efficiently train deep neural networks remains to be thoroughly solved. The widely used minibatch stochastic gradient descent (SGD) still needs to be accelerated. As a promising tool to better understand the learning dynamic of minibatch SGD, the information bottleneck (IB) theory claims that the optimization process consists of an initial fitting phase and the following compression phase. Based on this principle, we further study typicality sampling, an efficient data selection method, and propose a new explanation of how it helps accelerate the training process of the deep networks. We show that the fitting phase depicted in the IB theory will be boosted with a high signal-to-noise ratio of gradient approximation if the typicality sampling is appropriately adopted. Furthermore, this finding also implies that the prior information of the training set is critical to the optimization process, and the better use of the most important data can help the information flow through the bottleneck faster. Both theoretical analysis and experimental results on synthetic and real-world datasets demonstrate our conclusions.

Machine learning, especially deep neural networks, has developed rapidly in fields, including computer vision, speech recognition, and reinforcement learning. Although minibatch stochastic gradient descent (SGD) is one of the most popular stochastic optimization methods for training deep networks, it shows a slow convergence rate due to the large noise in the gradient approximation. In this article, we attempt to remedy this problem by building a more efficient batch selection method based on typicality sampling, which reduces the error of gradient estimation in conventional minibatch SGD. We analyze the convergence rate of the resulting typical batch SGD algorithm and compare the convergence properties between the minibatch SGD and the algorithm. Experimental results demonstrate that our batch selection scheme works well and more complex minibatch SGD variants can benefit from the proposed batch selection strategy.

Bug triage is a process where bugs are assigned to developers.In large open source projects such as Mozilla and Eclipse, bug triage is time-consuming because numerous bugs are submitted everyday.To improve bug triage, many studies have proposed automatic approaches to recommend proper developers for resolving bugs.These approaches are based on machine learning algorithms, which treat bug triage like text classification.Although they are effective, the accuracy of them can be further improved.Our goal is to propose a method not only has good performance but also is simple.We propose a method based on relevant search technique to recommend developers for the given bugs.First, we construct an index for bugs to make them searchable.Then, for a given bug to be assigned, we utilize the index to search for the bugs related to it.Finally, we analyze these related bugs and recommend developers based on them.We conduct experiments on bugs of Mozilla and Eclipse to evaluate our method.The results indicate that our method has a good performance and outperforms machine learning algorithms like Naïve Bayes and SVM.