A central problem in quantum mechanics involves solving the Electronic Schrodinger Equation for a molecule or material. The Variational Monte Carlo approach to this problem approximates a particular variational objective via sampling, and then optimizes this approximated objective over a chosen parameterized family of wavefunctions, known as the ansatz. Recently neural networks have been used as the ansatz, with accompanying success. However, sampling from such wavefunctions has required the use of a Markov Chain Monte Carlo approach, which is inherently inefficient. In this work, we propose a solution to this problem via an ansatz which is cheap to sample from, yet satisfies the requisite quantum mechanical properties. We prove that a normalizing flow using the following two essential ingredients satisfies our requirements: (a) a base distribution which is constructed from Determinantal Point Processes; (b) flow layers which are equivariant to a particular subgroup of the permutation group. We then show how to construct both continuous and discrete normalizing flows which satisfy the requisite equivariance. We further demonstrate the manner in which the non-smooth nature ("cusps") of the wavefunction may be captured, and how the framework may be generalized to provide induction across multiple molecules. The resulting theoretical framework entails an efficient approach to solving the Electronic Schrodinger Equation.
相關內容
Natural Language Processing (NLP) techniques are being used more frequently to improve high-tech Augmentative and Alternative Communication (AAC), but many of these techniques are integrated without the inclusion of the users' perspectives. Autistic adults are particularly neglected in the design of AAC tools. We conducted in-depth interviews with 12 autistic adults to find the pain points of current AAC and determine what technological advances they might find helpful. We found that in addition to technological issues, there are many societal issues as well. We found 9 different categories of themes from our interviews: input flexibility, output flexibility, selecting or adapting AAC for a good fit, when to start or swap AAC, benefits, access as an adult, stumbling blocks for continued use, social concerns, and control of communication. In this paper, we go through these categories in depth and then suggest possible guidelines for developers, NLP researchers, and policy makers.
Stochastic gradient descent (SGD) is a promising method for solving large-scale inverse problems, due to its excellent scalability with respect to data size. In this work, we analyze a new data-driven regularized stochastic gradient descent for the efficient numerical solution of a class of nonlinear ill-posed inverse problems in infinite dimensional Hilbert spaces. At each step of the iteration, the method randomly selects one equation from the nonlinear system combined with a corresponding equation from the learned system based on training data to obtain a stochastic estimate of the gradient and then performs a descent step with the estimated gradient. We prove the regularizing property of this method under the tangential cone condition and a priori parameter choice and then derive the convergence rates under the additional source condition and range invariance conditions. Several numerical experiments are provided to complement the analysis.
Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge, while generating coherent sentences. Although the quality of the generated sentences is crucial, the diversity of the generation is equally important because it reflects the model's ability to use a range of commonsense knowledge facts. Large Language Models (LLMs) have shown proficiency in enhancing the generation quality across various tasks through in-context learning (ICL) using given examples without the need for any fine-tuning. However, the diversity aspect in LLM outputs has not been systematically studied before. To address this, we propose a simple method that diversifies the LLM generations, while preserving their quality. Experimental results on three benchmark GCR datasets show that our method achieves an ideal balance between the quality and diversity. Moreover, the sentences generated by our proposed method can be used as training data to improve diversity in existing commonsense generators.
Automatic Sign Language (SL) recognition is an important task in the computer vision community. To build a robust SL recognition system, we need a considerable amount of data which is lacking particularly in Indian sign language (ISL). In this paper, we introduce a large-scale isolated ISL dataset and a novel SL recognition model based on skeleton graph structure. The dataset covers 2002 daily used common words in the deaf community recorded by 20 (10 male and 10 female) deaf adult signers (contains 40033 videos). We propose a SL recognition model namely Hierarchical Windowed Graph Attention Network (HWGAT) by utilizing the human upper body skeleton graph. The HWGAT tries to capture distinctive motions by giving attention to different body parts induced by the human skeleton graph. The utility of the proposed dataset and the usefulness of our model are evaluated through extensive experiments. We pre-trained the proposed model on the presented dataset and fine-tuned it across different sign language datasets further boosting the performance of 1.10, 0.46, 0.78, and 6.84 percentage points on INCLUDE, LSA64, AUTSL and WLASL respectively compared to the existing state-of-the-art keypoints-based models.
We study the problem of blind super-resolution, which can be formulated as a low-rank matrix recovery problem via vectorized Hankel lift (VHL). The previous gradient descent method based on VHL named PGD-VHL relies on additional regularization such as the projection and balancing penalty, exhibiting a suboptimal iteration complexity. In this paper, we propose a simpler unconstrained optimization problem without the above two types of regularization and develop two new and provable gradient methods named VGD-VHL and ScalGD-VHL. A novel and sharp analysis is provided for the theoretical guarantees of our algorithms, which demonstrates that our methods offer lower iteration complexity than PGD-VHL. In addition, ScalGD-VHL has the lowest iteration complexity while being independent of the condition number. Furthermore, our novel analysis reveals that the blind super-resolution problem is less incoherence-demanding, thereby eliminating the necessity for incoherent projections to achieve linear convergence. Empirical results illustrate that our methods exhibit superior computational efficiency while achieving comparable recovery performance to prior arts.
We consider two symmetry metrics to detect partisan gerrymandering: the Mean-Median Difference (MM) and Partisan Bias (PB). To lay the groundwork for our main results, we first assert that the foundation of a partisan gerrymander is to draw a map so that the preferred party wins an extreme number of seats, and that both the Mean-Median Difference and Partisan Bias have been used to detect partisan gerrymandering. We then provide both a theoretical and empirical analysis of the Mean-Median Difference and Partisan Bias. In our theoretical analysis, we consider vote-share, seat-share pairs (V,S) for which one can construct election data having vote share V and seat share S, and turnout is equal in each district. We calculate the range of values that MM and PB can achieve on that constructed election data. In the process, we find the range of vote-share, seat share pairs (V,S) for which there is constructed election data with vote share V , seat share S, and MM = 0, and see that the corresponding range for PB is the same set of (V,S) pairs. We show how the set of such (V,S) pairs allowing for MM = 0 (and PB = 0) changes when turnout in each district is allowed to be different. By observing the results of this theoretical analysis, we give examples of how these two metrics are unable to detect when a map has an extreme number of districts won. Because these examples are constructed, we follow this with our empirical study, in which we show on 18 different U.S. maps that these two metrics are unable to detect when a map has an extreme number of districts won.
Despite being widely applied due to their exceptional capabilities, Large Language Models (LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce targeted vulnerabilities into LLMs by poisoning training samples and full-parameter fine-tuning. However, this kind of backdoor attack is limited since they require significant computational resources, especially as the size of LLMs increases. Besides, parameter-efficient fine-tuning (PEFT) offers an alternative but the restricted parameter updating may impede the alignment of triggers with target labels. In this study, we first verify that backdoor attacks with PEFT may encounter challenges in achieving feasible performance. To address these issues and improve the effectiveness of backdoor attacks with PEFT, we propose a novel backdoor attack algorithm from weak to strong based on contrastive knowledge distillation (W2SAttack). Specifically, we poison small-scale language models through full-parameter fine-tuning to serve as the teacher model. The teacher model then covertly transfers the backdoor to the large-scale student model through contrastive knowledge distillation, which employs PEFT. Theoretical analysis reveals that W2SAttack has the potential to augment the effectiveness of backdoor attacks. We demonstrate the superior performance of W2SAttack on classification tasks across four language models, four backdoor attack algorithms, and two different architectures of teacher models. Experimental results indicate success rates close to 100% for backdoor attacks targeting PEFT.
We present a technique for approximating solutions to the spectral fractional Laplacian, which is based on the Caffarelli-Silvestre extension and diagonalization. Our scheme uses the analytic solution to the associated eigenvalue problem in the extended dimension. We show its relation to a quadrature scheme. Numerical examples demonstrate the performance of the method.
Nowadays, many machine learning (ML) solutions to improve the wireless standard IEEE802.11p for Vehicular Adhoc Network (VANET) are commonly evaluated in the simulated world. At the same time, this approach could be cost-effective compared to real-world testing due to the high cost of vehicles. There is a risk of unexpected outcomes when these solutions are implemented in the real world, potentially leading to wasted resources. To mitigate this challenge, the hardware-in-the-loop is the way to move forward as it enables the opportunity to test in the real world and simulated worlds together. Therefore, we have developed what we believe is the pioneering hardware-in-the-loop for testing artificial intelligence, multiple services, and HD map data (LiDAR), in both simulated and real-world settings.
The current state of Advanced Persistent Threats (APT) attribution primarily relies on time-consuming manual processes. These include mapping incident artifacts onto threat attribution frameworks and employing expert reasoning to uncover the most likely responsible APT groups. This research aims to assist the threat analyst in the attribution process by presenting an attribution method named CAPTAIN (Comprehensive Advanced Persistent Threat AttrIbutioN). This novel APT attribution approach leverages the Tactics, Techniques, and Procedures (TTPs) employed by various APT groups in past attacks. CAPTAIN follows two significant development steps: baseline establishment and similarity measure for attack pattern matching. This method starts by maintaining a TTP database of APTs seen in past attacks as baseline behaviour of threat groups. The attribution process leverages the contextual information added by TTP sequences, which reflects the sequence of behaviours threat actors demonstrated during the attack on different kill-chain stages. Then, it compares the provided TTPs with established baseline to identify the most closely matching threat group. CAPTAIN introduces a novel similarity measure for APT group attack-pattern matching that calculates the similarity between TTP sequences. The proposed approach outperforms traditional similarity measures like Cosine, Euclidean, and Longest Common Subsequence (LCS) in performing attribution. Overall, CAPTAIN performs attribution with the precision of 61.36% (top-1) and 69.98% (top-2), surpassing the existing state-of-the-art attribution methods.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191