搜索结果：Searched

Diffusion models have demonstrated remarkable generation quality but at the cost of numerous function evaluations. Recently, advanced ODE-based solvers have been developed to mitigate the substantial computational demands of reverse-diffusion solving under limited sampling steps. However, these solvers, heavily inspired by Adams-like multistep methods, rely solely on t-related Lagrange interpolation. We show that t-related Lagrange interpolation is suboptimal for diffusion model and reveal a compact search space comprised of time steps and solver coefficients. Building on our analysis, we propose a novel differentiable solver search algorithm to identify more optimal solver. Equipped with the searched solver, rectified-flow models, e.g., SiT-XL/2 and FlowDCN-XL/2, achieve FID scores of 2.40 and 2.35, respectively, on ImageNet256 with only 10 steps. Meanwhile, DDPM model, DiT-XL/2, reaches a FID score of 2.33 with only 10 steps. Notably, our searched solver outperforms traditional solvers by a significant margin. Moreover, our searched solver demonstrates generality across various model architectures, resolutions, and model sizes.

Gradient descent typically converges to a single minimum of the training loss without mechanisms to explore alternative minima that may generalize better. Searching for diverse minima directly in high-dimensional parameter space is generally intractable. To address this, we propose a framework that performs training in two distinct phases: search in a tractable representation space (the space of intermediate activations) to find diverse representational solutions, and gradient-based learning in parameter space by regressing to those searched representations. Through evolutionary search, we discover representational solutions whose fitness and diversity scale with compute--larger populations and more generations produce better and more varied solutions. These representations prove to be learnable: networks trained by regressing to searched representations approach SGD's performance on MNIST, CIFAR-10, and CIFAR-100. Performance improves with search compute up to saturation. The resulting models differ qualitatively from networks trained with gradient descent, following different representational trajectories during training. This work demonstrates how future training algorithms coul

How to benefit from plenty of existing denoising designs? Few methods via Neural Architecture Search (NAS) intend to answer this question. However, these NAS-based denoising methods explore limited search space and are hard to extend in terms of search space due to high computational burden. To tackle these limitations, we propose the first search framework to explore mainstream denoising designs. In our framework, the search space consists of the network-level, the cell-level and the kernel-level search space, which aims to inherit as many denoising designs as possible. Coordinating search strategies are proposed to facilitate the extension of various denoising designs. In such a giant search space, it is laborious to search for an optimal architecture. To solve this dilemma, we introduce the first regularization, i.e., denoising prior-based regularization, which reduces the search difficulty. To get an efficient architecture, we introduce the other regularization, i.e., inference time-based regularization, optimizes the search process on model complexity. Based on our framework, our searched architecture achieves state-of-the-art results for image denoising on multiple real-world

We consider a class of zero-sum search games in which a Hider hides one or more target among a set of $n$ boxes. The boxes may require differing amount of time to search, and detection may be imperfect, so that there is a certain probability that a target may not be found when a box is searched, even when it is there. A Searcher must choose how to search the boxes sequentially, and wishes to minimize the expected time to find the target(s), whereas the Hider wishes to maximize this payoff. We review some known solutions to different cases of this game.

Binary Neural Networks (BNNs) have gained extensive attention for their superior inferencing efficiency and compression ratio compared to traditional full-precision networks. However, due to the unique characteristics of BNNs, designing a powerful binary architecture is challenging and often requires significant manpower. A promising solution is to utilize Neural Architecture Search (NAS) to assist in designing BNNs, but current NAS methods for BNNs are relatively straightforward and leave a performance gap between the searched models and manually designed ones. To address this gap, we propose a novel neural architecture search scheme for binary neural networks, named NAS-BNN. We first carefully design a search space based on the unique characteristics of BNNs. Then, we present three training strategies, which significantly enhance the training of supernet and boost the performance of all subnets. Our discovered binary model family outperforms previous BNNs for a wide range of operations (OPs) from 20M to 200M. For instance, we achieve 68.20% top-1 accuracy on ImageNet with only 57M OPs. In addition, we validate the transferability of these searched BNNs on the object detection tas

Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs). However, the best way to use data to search network architectures is still unclear and under exploration. Previous work has analyzed the necessity of having ground-truth labels in NAS and inspired broad interest. In this work, we take a further step to question whether real data is necessary for NAS to be effective. The answer to this question is important for applications with limited amount of accessible data, and can help people improve NAS by leveraging the extra flexibility of data generation. To explore if NAS needs real data, we construct three types of unreal datasets using: 1) randomly labeled real images; 2) generated images and labels; and 3) generated Gaussian noise with random labels. These datasets facilitate to analyze the generalization and expressivity of the searched architectures. We study the performance of architectures searched on these constructed datasets using popular differentiable NAS methods. Extensive experiments on CIFAR, ImageNet and CheXpert show that the searched architectures can achieve promising results compared with those derived from

Neural Architecture Search~(NAS) has attracted increasingly more attention in recent years because of its capability to design deep neural networks automatically. Among them, differential NAS approaches such as DARTS, have gained popularity for the search efficiency. However, they suffer from two main issues, the weak robustness to the performance collapse and the poor generalization ability of the searched architectures. To solve these two problems, a simple-but-efficient regularization method, termed as Beta-Decay, is proposed to regularize the DARTS-based NAS searching process. Specifically, Beta-Decay regularization can impose constraints to keep the value and variance of activated architecture parameters from too large. Furthermore, we provide in-depth theoretical analysis on how it works and why it works. Experimental results on NAS-Bench-201 show that our proposed method can help to stabilize the searching process and makes the searched network more transferable across different datasets. In addition, our search scheme shows an outstanding property of being less dependent on training time and data. Comprehensive experiments on a variety of search spaces and datasets validate

Recent works have demonstrated that deep learning (DL) based compressed sensing (CS) implementation can accelerate Magnetic Resonance (MR) Imaging by reconstructing MR images from sub-sampled k-space data. However, network architectures adopted in previous methods are all designed by handcraft. Neural Architecture Search (NAS) algorithms can automatically build neural network architectures which have outperformed human designed ones in several vision tasks. Inspired by this, here we proposed a novel and efficient network for the MR image reconstruction problem via NAS instead of manual attempts. Particularly, a specific cell structure, which was integrated into the model-driven MR reconstruction pipeline, was automatically searched from a flexible pre-defined operation search space in a differentiable manner. Experimental results show that our searched network can produce better reconstruction results compared to previous state-of-the-art methods in terms of PSNR and SSIM with 4-6 times fewer computation resources. Extensive experiments were conducted to analyze how hyper-parameters affect reconstruction performance and the searched structures. The generalizability of the searched

Completing missing facts is a fundamental task for temporal knowledge graphs (TKGs). Recently, graph neural network (GNN) based methods, which can simultaneously explore topological and temporal information, have become the state-of-the-art (SOTA) to complete TKGs. However, these studies are based on hand-designed architectures and fail to explore the diverse topological and temporal properties of TKG. To address this issue, we propose to use neural architecture search (NAS) to design data-specific message passing architecture for TKG completion. In particular, we develop a generalized framework to explore topological and temporal information in TKGs. Based on this framework, we design an expressive search space to fully capture various properties of different TKGs. Meanwhile, we adopt a search algorithm, which trains a supernet structure by sampling single path for efficient search with less cost. We further conduct extensive experiments on three benchmark datasets. The results show that the searched architectures by our method achieve the SOTA performances. Besides, the searched models can also implicitly reveal diverse properties in different TKGs. Our code is released in https:

Transformers exhibit great advantages in handling computer vision tasks. They model image classification tasks by utilizing a multi-head attention mechanism to process a series of patches consisting of split images. However, for complex tasks, Transformer in computer vision not only requires inheriting a bit of dynamic attention and global context, but also needs to introduce features concerning noise reduction, shifting, and scaling invariance of objects. Therefore, here we take a step forward to study the structural characteristics of Transformer and convolution and propose an architecture search method-Vision Transformer with Convolutions Architecture Search (VTCAS). The high-performance backbone network searched by VTCAS introduces the desirable features of convolutional neural networks into the Transformer architecture while maintaining the benefits of the multi-head attention mechanism. The searched block-based backbone network can extract feature maps at different scales. These features are compatible with a wider range of visual tasks, such as image classification (32 M parameters, 82.0% Top-1 accuracy on ImageNet-1K) and object detection (50.4% mAP on COCO2017). The propos

We consider a search and rescue game introduced recently by the first author. An immobile target or targets (for example, injured hikers) are hidden on a graph. The terrain is assumed to dangerous, so that when any given vertex of the graph is searched, there is a certain probability that the search will come to an end, otherwise with the complementary {\em success probability} the search can continue. A Searcher searches the graph with the aim of finding all the targets with maximum probability. Here, we focus on the game in the case that the graph is a cycle. In the case that there is only one target, we solve the game for equal success probabilities, and for a class of games with unequal success probabilities. For multiple targets and equal success probabilities, we give a solution for an adaptive Searcher and a solution in a special case for a non-adaptive Searcher. We also consider a continuous version of the model, giving a full solution for an adaptive Searcher and approximately optimal solutions in the non-adaptive case.

We describe the results of four new searches based on data samples from the 1992 - 1996 proton-antiproton 1.8 TeV Collider run at Fermilab. DZERO has searched for resonant slepton production in the two muon plus two jet channel. Using the R-parity violating mSUGRA model, smuon and smuon neutrino masses up to 280 GeV/c2 are excluded. CDF has searched for R-parity violating scalar top quark decays in two tau plus two jet events and set a mass limit of 119 GeV/c2. DZERO has searched for evidence of large extra dimensions in monojet production. Limits are set on M_D the fundamental mass scale, of 0.68 and 0.63 TeV for n = 4 and n = 6 extra dimensions. CDF has interpreted a search for new physics in photon + missing energy events as a search for a gravitino and alternatively as a search for effects of graviton production. A gravitino mass limit of 1.17*10**(-5) eV is set. Limits on M_D of 0.55, 0.58, and 0.60 TeV for n = 4, 6, and 8 are also determined.

I present three recent results from searches for exotic physics at the BaBar/PEP-II B-factory. These results span many of the samples produced at the B-factory, including B mesons, tau leptons, and Upsilon(3S) mesons. We have searched for CPT-violation in B mixing and find no significant deviation from the no-violation hypothesis. We have also searched for lepton-flavor-violating decays of the tau using tau- -> omega l- and tau- -> l+ l- l+ and their charge conjugates. We find no evidence for these processes and set upper limits on their branching fractions. Finally, we have searched for a low-mass Higgs boson in the decay Upsilon(3S) -> gamma A0, where the Higgs decays invisibly. We find no evidence for such a decay and set upper limits across a range of possible Higgs masses.

The LHC experiments have searched for and excluded many proposed Beyond the Standard Model (BSM) theories. However, there are many scenarios where LHC has little or no sensitivity. Electron-positron colliders offers a different avenue for searches for such phenomena.In this talk, we will review the expectations for searches for number of BSM models at the International Linear Collider (ILC). We will discuss new Higgs-like scalars, indirect BSM via Standard Model Effective Field Theory (SMEFT) fits, mono-photons, and SUSY in strongly or moderately compressed models.

As deep neural networks achieve unprecedented performance in various tasks, neural architecture search (NAS), a research field for designing neural network architectures with automated processes, is actively underway. More recently, differentiable NAS has a great impact by reducing the search cost to the level of training a single network. Besides, the search space that defines candidate architectures to be searched directly affects the performance of the final architecture. In this paper, we propose an adaptation scheme of the search space by introducing a search scope. The effectiveness of proposed method is demonstrated with ProxylessNAS for the image classification task. Furthermore, we visualize the trajectory of architecture parameter updates and provide insights to improve the architecture search.

The Isabelle Archive of Formal Proofs (AFP) has grown to over 500 articles in late 2019. Meanwhile, finding formalizations in it has not exactly become easier. At the time of writing, the site-specific AFP google search and the Isabelle find_theories resp. find_consts commands (that only work on imported theories) are still the only tools readily available to find formalizations in Isabelle. We present FindFacts, a novel domain-specific search tool for formal Isabelle theory content. Instead of utilizing term unification, we solve the problem with a classical drill-down search engine. We put special emphasis on scalability of the search system, so that the whole AFP can be searched interactively.

Vision Transformer has shown great visual representation power in substantial vision tasks such as recognition and detection, and thus been attracting fast-growing efforts on manually designing more effective architectures. In this paper, we propose to use neural architecture search to automate this process, by searching not only the architecture but also the search space. The central idea is to gradually evolve different search dimensions guided by their E-T Error computed using a weight-sharing supernet. Moreover, we provide design guidelines of general vision transformers with extensive analysis according to the space searching process, which could promote the understanding of vision transformer. Remarkably, the searched models, named S3 (short for Searching the Search Space), from the searched space achieve superior performance to recently proposed models, such as Swin, DeiT and ViT, when evaluated on ImageNet. The effectiveness of S3 is also illustrated on object detection, semantic segmentation and visual question answering, demonstrating its generality to downstream vision and vision-language tasks. Code and models will be available at https://github.com/microsoft/Cream.

We numerically study the quantum walk search algorithm of Shenvi, Kempe and Whaley [PRA \textbf{67} 052307] and the factors which affect its efficiency in finding an individual state from an unsorted set. Previous work has focused purely on the effects of the dimensionality of the dataset to be searched. Here, we consider the effects of interpolating between dimensions, connectivity of the dataset, and the possibility of disorder in the underlying substrate: all these factors affect the efficiency of the search algorithm. We show that, as well as the strong dependence on the spatial dimension of the structure to be searched, there are also secondary dependencies on the connectivity and symmetry of the lattice, with greater connectivity providing a more efficient algorithm. In addition, we also show that the algorithm can tolerate a non-trivial level of disorder in the underlying substrate.