A novel first-order method is proposed for training generative adversarial networks (GANs). It modifies the Gauss-Newton method to approximate the min-max Hessian and uses the Sherman-Morrison inversion formula to calculate the inverse. The method corresponds to a fixed-point method that ensures necessary contraction. To evaluate its effectiveness, numerical experiments are conducted on various datasets commonly used in image generation tasks, such as MNIST, Fashion MNIST, CIFAR10, FFHQ, and LSUN. Our method is capable of generating high-fidelity images with greater diversity across multiple datasets. It also achieves the highest inception score for CIFAR10 among all compared methods, including state-of-the-art second-order methods. Additionally, its execution time is comparable to that of first-order min-max methods.

1Generative AI has seen remarkable growth over the past few years, with diffusion models being state-of-the-art for image generation. This study investigates the use of diffusion models in artificial data generation for electronic circuits to enhance the accuracy of subsequent machine learning models in tasks such as performance assessment, design, and testing when training data is usually known to be very limited. We utilize simulations in the HSPICE design environment with 22nm CMOS technology nodes to obtain representative real training data for our proposed diffusion model. Our results demonstrate the close resemblance of synthetic data using diffusion models to real data. We validate the quality of generated data and demonstrate that data augmentation is certainly effective in the predictive analysis of VLSI design for digital circuits.

We propose a second order gradient based method with ADAM and RMSprop for the training of generative adversarial networks. The proposed method is fastest to obtain similar accuracy when compared to prominent second order methods. Unlike state-of-the-art recent methods, it does not require solving a linear system, or it does not require additional mixed second derivative terms. We derive the fixed point iteration corresponding to proposed method, and show that the proposed method is convergent. The proposed method produces better or comparable inception scores, and comparable quality of images compared to other recently proposed state-of-the-art second order methods. Compared to first order methods such as ADAM, it produces significantly better inception scores. The proposed method is compared and validated on popular datasets such as FFHQ, LSUN, CIFAR10, MNIST, and Fashion MNIST for image generation tasks.

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number of agents 2) This, combined with the reward sparseness and environment noise, leads to large sample requirements for accurate learning. We show that regularising the critic with spectral normalization (SN) enables it to learn more robustly, even in multi-agent on-policy sparse reward scenarios. Our experiments show that the regularised critic is quickly able to learn from the sparse rewarding experience in the complex SMAC and RWARE domains. These findings highlight the importance of regularisation in the critic for stable learning.

Extreme multi-label (XML) classification refers to the task of supervised multi-label learning that involves a large number of labels. Hence, scalability of the classifier with increasing label dimension is an important consideration. In this paper, we develop a method called LightDXML which modifies the recently developed deep learning based XML framework by using label embeddings instead of feature embedding for negative sampling and iterating cyclically through three major phases: (1) proxy training of label embeddings (2) shortlisting of labels for negative sampling and (3) final classifier training using the negative samples. Consequently, LightDXML also removes the requirement of a re-ranker module, thereby, leading to further savings on time and memory requirements. The proposed method achieves the best of both worlds: while the training time, model size and prediction times are on par or better compared to the tree-based methods, it attains much better prediction accuracy that is on par with the deep learning based methods. Moreover, the proposed approach achieves the best tail-label prediction accuracy over most state-of-the-art XML methods on some of the large datasets.

In our work, we propose a novel yet simple approach to obtain an adaptive learning rate for gradient-based descent methods on classification tasks. Instead of the traditional approach of selecting adaptive learning rates via the decayed expectation of gradient-based terms, we use the angle between the current gradient and the new gradient: this new gradient is computed from the direction orthogonal to the current gradient, which further helps us in determining a better adaptive learning rate based on angle history, thereby, leading to relatively better accuracy compared to the existing state-of-the-art optimizers. On a wide variety of benchmark datasets with prominent image classification architectures such as ResNet, DenseNet, Efficient-Net, and VGG, we find that our method leads to the highest accuracy in most of the datasets. Moreover, we prove that our method is convergent.

Transformers, which were introduced for solving the task of machine translation, have expanded their utility in multiple domains. A recent application of transformers is in solving elementary mathematics problems. In this paper, we use a hybrid tokenization technique for encoding the mathematics and science problems and answers, which is used to train the transformer. We compare the performance of our tokenization with that of the char-to-char tokenzation in solving various types of mathematics and science problems. We discuss the accuracy, memory usage, and time to train the model with proposed tokenization. The proposed tokenization shows higher accuracy for some problems, and requires lesser memory compared to char-to-char tokenization. We propose an extended dataset of science and mathematics problems that consists of billions of samples in question-answer format in raw text. Code and Dataset: https://github.com/misterpawan/scimat2.

Recent approaches to the tensor completion problem have often overlooked the nonnegative structure of the data. We consider the problem of learning a nonnegative low-rank tensor, and using duality theory, we propose a novel factorization of such tensors. The factorization decouples the nonnegative constraints from the low-rank constraints. The resulting problem is an optimization problem on manifolds, and we propose a variant of Riemannian conjugate gradients to solve it. We test the proposed algorithm across various tasks such as colour image inpainting, video completion, and hyperspectral image completion. Experimental results show that the proposed method outperforms many state-of-the-art tensor completion algorithms.

The bundle adjustment (BA) problem is formulated as a non linear least squares problem which, requires the solution of a linear system. For solving this system, we present the design and implementation of a fast preconditioned solver. The proposed preconditioner is based on the deflation of the largest eigenvalues of the Hessian. We also derive an estimate of the condition number of the preconditioned system. Numerical experiments on problems from the BAL dataset [3] suggest that our solver is the fastest, sometimes, by a factor of five, when compared to the current state-of-the-art solvers for bundle adjustment.

We present the design and implementation of Two-Grid Preconditioned Bundle Adjustment (TPBA), a robust and efficient technique for solving the non-linear least squares problem that arises in bundle adjustment. Bundle adjustment (BA) methods for multi-view reconstruction formulate the BA problem as a non-linear least squares problem which is solved by some variant of the traditional Levenberg-Marquardt (LM) algorithm. Most of the computation in LM goes into repeatedly solving the normal equations that arise as a result of linearizing the objective function. To solve these system of equations we use the Generalized Minimal Residual (GMRES) method, which is preconditioned using a deflated algebraic two-grid method. To the best of our knowledge this is the first time that a deflated algebraic two-grid preconditioner has been used along with GMRES, for solving a problem in the computer vision domain. We show that the proposed method is several times faster than the direct method and block Jacobi preconditioned GMRES.

In this study, elliptic curve cryptography (ECC) is elected for tenant authentication, data encryption, and data decryption due to its minimum key size. The proposed ECC‐based authentication approach allows the authorised person to access private data; it protects different related attacks effectively. To develop more secure data encryption, the authors have combined a nature‐inspired optimisation, such as a moth search algorithm (MSA) with ECC, to select the correct and optimal value of the elliptic curve. The proposed encryption and decryption approach combines DNA encoding with the ECC encryption algorithm. The mechanism of DNA encoded ECC provided multi‐level security with less computational power. The security analysis of the proposed method has been provided to prove its effectiveness against certain attacks, such as denial‐of‐service attack, impersonation attack, reply attack, plaintext attack and chosen‐ciphertext attack. The experimental result is evaluated based on encryption time, decryption time, throughput and key size of the security model. The average execution time of the proposed encryption and decryption is only 83.153 and 86.076 s, respectively. From the evaluation, it is clearly determined that the proposed technique provides two‐layer security with minimum key size and less storage space.

In conjugate gradient method to solve partial differential equations, matrix vector operations are required in each iteration; these matrix vector operations can be implemented as 5 point finite difference stencil operations on the grid without explicitely constructing the matrix. We show that a pipelined and superscalar design using high level synthesis (HLS) leads to a significant reduction in latencies for two variants of conjugate gradient methods considered. When comparing these two, we show that the second method has roughly two times lower latency than the former given the same degree of superscalarity. These reductions in latencies for the newer variant of CG is due to parallel implementations of stencil operation on subdomains of the grid, and due to overlap of these stencil operations with dot product operations. In a superscalar design for the stencil operation, the computational domain needs to be partitioned, and boundary data needs to be copied, which requires padding. We propose a novel traversal of the grid for 2D domain decomposition that leads to reduction in latency cost involved with padding. The FPGA implementation of CG is roughly 7 times faster than state-of- the-art sequential implementation, and roughly 4 times faster than state-of-the-art CUDA library parallel implementation for the linear system of dimension 10000 x 10000.

In this paper, we describe Transzaar - an AI powered tool that offers computer aided translation (CAT) functionality: pre-translation analysis, post-editing machine translated content, translation prediction, text aligning, extensive logging and integration with several machine translation (MT) systems. Transzaar aids a human translator to perform various language processing tasks, viz., Translation, Transliteration, Localization, and other kinds of Text Analysis tasks. Using Transzaar, human translators can post-edit the machine translated content, to improve fluency and accuracy of the translated content to match the naturalness of human translation while delivering with better turn-around time. Transzaar aids the process of post-editing, thereby increasing the productivity of human translators by 2-3 folds within couple of months of usage for certain language pairs. It collects feedback continuously, which helps the MT system to further learn and improve periodically, with the additional new generated data-set.

Sampark is machine translation system providing translations among nine pairs of Indian languages. Machine translation system is a class of natural language processing applications that is far more complex and highly compute intensive in nature. As the load on the deployed system increases, optimization becomes a challenge. Caching is one of the available options to improve the performance of a software system with increasing load which exhibit the characteristics of locality of reference. Sampark MT system being a natural language processing application exhibits this characteristic. Memcached is a well-known, simple, in-memory caching solution that has been applied to improve the performance of several distributed web applications in the past. This paper describes how memcached has been applied to improve the performance of Sampark machine translation service which is deployed on a large cluster of machines. By applying distributed caching to MT system the performance of the system has improved upto 40%.

Dashboard is an integration, validation, and visualization tool for Natural Language Processing (NLP) applications. It provides infrastructural facilities using which individual NLP modules may be evaluated and refined, and multiple NLP modules may be combined to build a large end-user NLP system. It helps the system integration team to integrate and validate the NLP system. The tool provides a visualization interface that helps the developers to profile (time and memory) each module. It helps researchers to evaluate and compare their module with the earlier versions of same module. The tool promotes reuse of existing NLP modules. Enriched Dashboard supports execution of modules on heterogeneous platforms. It supports execution of modules that are distributed i.e., located on different machines. It has a powerful notation to define the runtime properties of the NLP modules. It provides an easy-to-use graphical interface that is developed using Eclipse RCP. The user can choose a perspective (view) that allows him to perform his task better. Additionally, Eclipse RCP provides a plugin architecture, hence additional end-user functionalities can be easily added to the tool.