Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning

As a marriage between offline RL and meta-RL, the advent of offline meta-reinforcement learning (OMRL) has shown great promise in enabling RL agents to multi-task and quickly adapt while acquiring knowledge safely. Among which, Context-based OMRL (COMRL) as a popular paradigm, aims to learn a universal policy conditioned on effective task representations. In this work, by examining several key milestones in the field of COMRL, we propose to integrate these seemingly independent methodologies into a unified information theoretic framework. Most importantly, we show that the pre-existing COMRL algorithms are essentially optimizing the same mutual information objective between the task variable $\boldsymbol{M}$ and its latent representation $\boldsymbol{Z}$ by implementing various approximate bounds. Based on the theoretical insight and the information bottleneck principle, we arrive at a novel algorithm dubbed UNICORN, which exhibits remarkable generalization across a broad spectrum of RL benchmarks, context shift scenarios, data qualities and deep learning architectures, attaining the new state-of-the-art. We believe that our framework could open up avenues for new optimality bounds and COMRL algorithms.

HyperEditor: Achieving Both Authenticity and Cross-Domain Capability in Image Editing via Hypernetworks

Editing real images authentically while also achieving cross-domain editing remains a challenge. Recent studies have focused on converting real images into latent codes and accomplishing image editing by manipulating these codes. However, merely manipulating the latent codes would constrain the edited images to the generator's image domain, hindering the attainment of diverse editing goals. In response, we propose an innovative image editing method called HyperEditor, which utilizes weight factors generated by hypernetworks to reassign the weights of the pre-trained StyleGAN2's generator. Guided by CLIP's cross-modal image-text semantic alignment, this innovative approach enables us to simultaneously accomplish authentic attribute editing and cross-domain style transfer, a capability not realized in previous methods. Additionally, we ascertain that modifying only the weights of specific layers in the generator can yield an equivalent editing result. Therefore, we introduce an adaptive layer selector, enabling our hypernetworks to autonomously identify the layers requiring output weight factors, which can further improve our hypernetworks' efficiency. Extensive experiments on abundant challenging datasets demonstrate the effectiveness of our method.

Simple Semantic-Aided Few-Shot Learning

Learning from a limited amount of data, namely Few-Shot Learning, stands out as a challenging computer vision task. Several works exploit semantics and design complicated semantic fusion mechanisms to compensate for rare representative features within restricted data. However, relying on naive semantics such as class names introduces biases due to their brevity, while acquiring extensive semantics from external knowledge takes a huge time and effort. This limitation severely constrains the potential of semantics in few-shot learning. In this paper, we design an automatic way called Semantic Evolution to generate high-quality semantics. The incorporation of high-quality semantics alleviates the need for complex network structures and learning algorithms used in previous works. Hence, we employ a simple two-layer network termed Semantic Alignment Network to transform semantics and visual features into robust class prototypes with rich discriminative features for few-shot classification. The experimental results show our framework outperforms all previous methods on five benchmarks, demonstrating a simple network with high-quality semantics can beat intricate multi-modal modules on few-shot classification tasks.

SCAN-MUSIC: An Efficient Super-resolution Algorithm for Single Snapshot Wide-band Line Spectral Estimation

We propose an efficient algorithm for reconstructing one-dimensional wide-band line spectra from their Fourier data in a bounded interval $[-\Omega,\Omega]$. While traditional subspace methods such as MUSIC achieve super-resolution for closely separated line spectra, their computational cost is high, particularly for wide-band line spectra. To address this issue, we proposed a scalable algorithm termed SCAN-MUSIC that scans the spectral domain using a fixed Gaussian window and then reconstructs the line spectra falling into the window at each time. For line spectra with cluster structure, we further refine the proposed algorithm using the annihilating filter technique. Both algorithms can significantly reduce the computational complexity of the standard MUSIC algorithm with a moderate loss of resolution. Moreover, in terms of speed, their performance is comparable to the state-of-the-art algorithms, while being more reliable for reconstructing line spectra with cluster structure. The algorithms are supplemented with theoretical analyses of error estimates, sampling complexity, computational complexity, and computational limit.

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization

Designing and deriving effective model-based reinforcement learning (MBRL) algorithms with a performance improvement guarantee is challenging, mainly attributed to the high coupling between model learning and policy optimization. Many prior methods that rely on return discrepancy to guide model learning ignore the impacts of model shift, which can lead to performance deterioration due to excessive model updates. Other methods use performance difference bound to explicitly consider model shift. However, these methods rely on a fixed threshold to constrain model shift, resulting in a heavy dependence on the threshold and a lack of adaptability during the training process. In this paper, we theoretically derive an optimization objective that can unify model shift and model bias and then formulate a fine-tuning process. This process adaptively adjusts the model updates to get a performance improvement guarantee while avoiding model overfitting. Based on these, we develop a straightforward algorithm USB-PO (Unified model Shift and model Bias Policy Optimization). Empirical results show that USB-PO achieves state-of-the-art performance on several challenging benchmark tasks.

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery

Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. To ensure safety during and after training process, existing methods tend to adopt overly conservative policy to avoid unsafe situations. However, overly conservative policy severely hinders the exploration, and makes the algorithms substantially less rewarding. In this paper, we propose a method to construct a boundary that discriminates safe and unsafe states. The boundary we construct is equivalent to distinguishing dead-end states, indicating the maximum extent to which safe exploration is guaranteed, and thus has minimum limitation on exploration. Similar to Recovery Reinforcement Learning, we utilize a decoupled RL framework to learn two policies, (1) a task policy that only considers improving the task performance, and (2) a recovery policy that maximizes safety. The recovery policy and a corresponding safety critic are pretrained on an offline dataset, in which the safety critic evaluates upper bound of safety in each state as awareness of environmental safety for the agent. During online training, a behavior correction mechanism is adopted, ensuring the agent to interact with the environment using safe actions only. Finally, experiments of continuous control tasks demonstrate that our approach has better task performance with less safety violations than state-of-the-art algorithms.

IFF: A Super-resolution Algorithm for Multiple Measurements

We consider the problem of reconstructing one-dimensional point sources from their Fourier measurements in a bounded interval $[-\Omega, \Omega]$. This problem is known to be challenging in the regime where the spacing of the sources is below the Rayleigh length $\frac{\pi}{\Omega}$. In this paper, we propose a super-resolution algorithm, called Iterative Focusing-localization and Filtering (IFF), to resolve closely spaced point sources from their multiple measurements that are obtained by using multiple unknown illumination patterns. The new proposed algorithm has a distinct feature in that it reconstructs the point sources one by one in an iterative manner and hence requires no prior information about the source numbers. The new feature also allows for a subsampling strategy that can circumvent the computation of singular-value decomposition for large matrices as in the usual subspace methods. A theoretical analysis of the methods behind the algorithm is also provided. The derived results imply a phase transition phenomenon in the reconstruction of source locations which is confirmed in numerical experiments. Numerical results show that the algorithm can achieve a stable reconstruction for point sources with a minimum separation distance that is close to the theoretical limit. The algorithm can be generalized to higher dimensions.

A measurement decoupling based fast algorithm for super-resolving point sources with multi-cluster structure

We consider the problem of resolving closely spaced point sources in one dimension from their Fourier data in a bounded domain. Classical subspace methods (e.g., MUSIC algorithm, Matrix Pencil method, etc.) show great superiority in resolving closely spaced sources, but their computational cost is usually heavy. This is especially the case for point sources with a multi-cluster structure which requires processing large-sized data matrix resulted from highly sampled measurements. To address this issue, we propose a fast algorithm termed D-MUSIC, based on a measurement decoupling strategy. We demonstrate theoretically that for point sources with a known cluster structure, their measurement can be decoupled into local measurements of each of the clusters by solving a system of linear equations that are obtained by using a multipole basis. We further develop a subsampled MUSIC algorithm to detect the cluster structure and utilize it to decouple the global measurement. In the end, the MUSIC algorithm was applied to each local measurement to resolve point sources therein. Compared to the standard MUSIC algorithm, the proposed algorithm has comparable super-resolving capability while having a much lower computational complexity.

Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images

Automatic breast lesion segmentation in ultrasound helps to diagnose breast cancer, which is one of the dreadful diseases that affect women globally. Segmenting breast regions accurately from ultrasound image is a challenging task due to the inherent speckle artifacts, blurry breast lesion boundaries, and inhomogeneous intensity distributions inside the breast lesion regions. Recently, convolutional neural networks (CNNs) have demonstrated remarkable results in medical image segmentation tasks. However, the convolutional operations in a CNN often focus on local regions, which suffer from limited capabilities in capturing long-range dependencies of the input ultrasound image, resulting in degraded breast lesion segmentation accuracy. In this paper, we develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection (BD) modules for boosting the breast ultrasound lesion segmentation. The GGB utilizes the multi-layer integrated feature map as a guidance information to learn the long-range non-local dependencies from both spatial and channel domains. The BD modules learn additional breast lesion boundary map to enhance the boundary quality of a segmentation result refinement. Experimental results on a public dataset and a collected dataset show that our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation. Moreover, we also show the application of our network on the ultrasound prostate segmentation, in which our method better identifies prostate regions than state-of-the-art networks.

Mathematical Theory of Computational Resolution Limit in Multi-dimensions

Resolving a linear combination of point sources from their band-limited Fourier data is a fundamental problem in imaging and signal processing. With the incomplete Fourier data and the inevitable noise in the measurement, there is a fundamental limit on the separation distance between point sources that can be resolved. This is the so-called resolution limit problem. Characterization of this resolution limit is still a long-standing puzzle despite the prevalent use of the classic Rayleigh limit. It is well-known that Rayleigh limit is heuristic and its drawbacks become prominent when dealing with data that is subjected to delicate processing, as is what modern computational imaging methods do. Therefore, more precise characterization of the resolution limit becomes increasingly necessary with the development of data processing methods. For this purpose, we developed a theory of "computational resolution limit" for both number detection and support recovery in one dimension in [arXiv:2003.02917[cs.IT], arXiv:1912.05430[eess.IV]]. In this paper, we extend the one-dimensional theory to multi-dimensions. More precisely, we define and quantitatively characterize the "computational resolution limit" for the number detection and support recovery problems in a general k-dimensional space. Our results indicate that there exists a phase transition phenomenon regarding to the super-resolution factor and the signal-to-noise ratio in each of the two recovery problems. Our main results are derived using a subspace projection strategy. Finally, to verify the theory, we proposed deterministic subspace projection based algorithms for the number detection and support recovery problems in dimension two and three. The numerical results confirm the phase transition phenomenon predicted by the theory.