Abhinav Anand

Abhinav Anand, Jakob S. Kottmann, Alán Aspuru-Guzik

As we continue to find applications where the currently available noisy devices exhibit an advantage over their classical counterparts, the efficient use of quantum resources is highly desirable. The notion of quantum autoencoders was proposed as a way for the compression of quantum information to reduce resource requirements. Here, we present a strategy to design quantum autoencoders using evolutionary algorithms for transforming quantum information into lower-dimensional representations. We successfully demonstrate the initial applications of the algorithm for compressing different families of quantum states. In particular, we point out that using a restricted gate set in the algorithm allows for efficient simulation of the generated circuits. This approach opens the possibility of using classical logic to find low representations of quantum data, using fewer computational resources.

Mingze Wu, Abhinav Anand, Shweta Verma et al.

Post-training using online reinforcement learning (RL) is an important training step for LLMs, including code-generating models. However, online RL for code generation involves LLM inference and verification of the generated output, which can take considerable time and resources. In this paper, we explore the application of offline RL to code-generating models by leveraging existing code datasets. Our experiments demonstrate that offline RL is an effective training strategy for improving LLM performance. We show that offline RL can be especially beneficial for small LLMs and challenging coding problems.

Erfan Aghadavoodi Jolfaei, Daniel Maninger, Abhinav Anand et al.

Large language models show strong potential for automated code generation, but lack guarantees for correctness, quality, safety, and domain-specific constraints. For instance in robotics, where code generation is increasingly being used for planning and executing actions, awareness of the environment and physical constraints is critical. To facilitate the adaption of code-generating LLMs to diverse requirements, including domain-specific ones, we present a reinforcement learning framework that fine-tunes pre-trained LLMs using proximal policy optimization. Our customizable execution-aware reward formula captures and optimizes syntax, functional correctness, code style, security, and simulator executability. A token-level reward mapping mechanism enables effective credit assignment from execution outcomes to generated tokens. The framework is evaluated on general-purpose code generation (MBPP/MBPP+) and robotic program synthesis (RoboEval). The results show substantial improvements in functional correctness and simulator executability, including an absolute pass@1 increase of 19% on MBPP and a reduction in execution failures by 51% on RoboEval. These findings demonstrate that structured reinforcement learning can effectively align language models to correct program generation and domain-specific requirements.

Ishaan R Kale, Mandar S Sapre, Ayush Khedkar et al.

A range of complicated real-world problems have inspired the development of several optimization methods. Here, a novel hybrid version of the Ant colony optimization (ACO) method is developed using the sample space reduction technique of the Cohort Intelligence (CI) Algorithm. The algorithm is developed, and accuracy is tested by solving 35 standard benchmark test functions. Furthermore, the constrained version of the algorithm is used to solve two mechanical design problems involving stepped cantilever beams and I-section beams. The effectiveness of the proposed technique of solution is evaluated relative to contemporary algorithmic approaches that are already in use. The results show that our proposed hybrid ACO-CI algorithm will take lesser number of iterations to produce the desired output which means lesser computational time. For the minimization of weight of stepped cantilever beam and deflection in I-section beam a proposed hybrid ACO-CI algorithm yielded best results when compared to other existing algorithms. The proposed work could be investigate for variegated real world applications encompassing domains of engineering, combinatorial and health care problems.

Marina Sakharova, Abhinav Anand, Mira Mezini

Code-generating Large Language Models (LLMs) have become essential tools in modern software development, enhancing productivity and accelerating development. This paper aims to investigate the fine-tuning of code-generating LLMs using Reinforcement Learning and Direct Preference Optimization, further improving their performance. To achieve this, we enhance the training data for the reward model with the help of symbolic execution techniques, ensuring more comprehensive and objective data. With symbolic execution, we create a custom dataset that better captures the nuances in code evaluation. Our reward models, fine-tuned on this dataset, demonstrate significant improvements over the baseline, CodeRL, in estimating the quality of generated code. Our code-generating LLMs, trained with the help of reward model feedback, achieve similar results compared to the CodeRL benchmark.

Jiali Wu, Abhinav Anand, Shweta Verma et al.

State Space Models (SSMs) have emerged as an efficient alternative to the transformer architecture. Recent studies show that SSMs can match or surpass Transformers on code understanding tasks, such as code retrieval, when trained under similar conditions. However, their internal mechanisms remain a black box. We present the first systematic analysis of what SSM-based code models actually learn and perform the first comparative analysis of SSM and Transformer-based code models. Our analysis reveals that SSMs outperform Transformers at capturing code syntax and semantics in pretraining but forgets certain syntactic and semantic relations during fine-tuning on task, especially when the task emphasizes short-range dependencies. To diagnose this, we introduce SSM-Interpret, a frequency-domain framework that exposes a spectral shift toward short-range dependencies during fine-tuning. Guided by these findings, we propose architectural modifications that significantly improve the performance of SSM-based code model, validating that our analysis directly enables better models.

Srividya Ravikumar, Abhinav Anand, Shweta Verma et al.

Although state-space models (SSMs) have demonstrated strong performance on long-sequence benchmarks, most research has emphasized predictive accuracy rather than interpretability. In this work, we present the first systematic kernel interpretability study of the diagonalized state-space model (S4D) trained on a real-world task (vulnerability detection in source code). Through time and frequency domain analysis of the S4D kernel, we show that the long-range modeling capability of S4D varies significantly under different model architectures, affecting model performance. For instance, we show that the depending on the architecture, S4D kernel can behave as low-pass, band-pass or high-pass filter. The insights from our analysis can guide future work in designing better S4D-based models.

Shweta Verma, Abhinav Anand, Mira Mezini

Although transformers dominate many code-specific tasks, they have significant limitations. This paper explores State Space Models (SSMs) as a promising alternative for code understanding tasks such as retrieval, classification, and clone detection. We introduce CodeSSM, the first SSM-based model trained on code corpora to assess its effectiveness. Our results demonstrate that SSMs are more sample-efficient and can extrapolate to longer contexts beyond the pretraining length. Extensive experiments show that SSMs offer a viable alternative to transformers, addressing several their limitations. Additionally, CodeSSM reduces memory usage by up to 64\% compared to transformers at a context length of 2048, with greater savings as context length grows.

Abhinav Anand, Shweta Verma, Krishna Narasimhan et al.

Large Language Models trained on code corpora (code-LLMs) have demonstrated impressive performance in various coding assistance tasks. However, despite their increased size and training dataset, code-LLMs still have limitations such as suggesting codes with syntactic errors, variable misuse etc. Some studies argue that code-LLMs perform well on coding tasks because they use self-attention and hidden representations to encode relations among input tokens. However, previous works have not studied what code properties are not encoded by code-LLMs. In this paper, we conduct a fine-grained analysis of attention maps and hidden representations of code-LLMs. Our study indicates that code-LLMs only encode relations among specific subsets of input tokens. Specifically, by categorizing input tokens into syntactic tokens and identifiers, we found that models encode relations among syntactic tokens and among identifiers, but they fail to encode relations between syntactic tokens and identifiers. We also found that fine-tuned models encode these relations poorly compared to their pre-trained counterparts. Additionally, larger models with billions of parameters encode significantly less information about code than models with only a few hundred million parameters.

Kishor Bharti, Alba Cervera-Lierta, Thi Ha Kyaw et al.

A universal fault-tolerant quantum computer that can solve efficiently problems such as integer factorization and unstructured database search requires millions of qubits with low error rates and long coherence times. While the experimental advancement towards realizing such devices will potentially take decades of research, noisy intermediate-scale quantum (NISQ) computers already exist. These computers are composed of hundreds of noisy qubits, i.e. qubits that are not error-corrected, and therefore perform imperfect operations in a limited coherence time. In the search for quantum advantage with these devices, algorithms have been proposed for applications in various disciplines spanning physics, machine learning, quantum chemistry and combinatorial optimization. The goal of such algorithms is to leverage the limited available resources to perform classically challenging tasks. In this review, we provide a thorough summary of NISQ computational paradigms and algorithms. We discuss the key structure of these algorithms, their limitations, and advantages. We additionally provide a comprehensive overview of various benchmarking and software tools useful for programming and testing NISQ devices.

Abhinav Anand, Matthias Degroote, Alán Aspuru-Guzik

Natural evolutionary strategies (NES) are a family of gradient-free black-box optimization algorithms. This study illustrates their use for the optimization of randomly-initialized parametrized quantum circuits (PQCs) in the region of vanishing gradients. We show that using the NES gradient estimator the exponential decrease in variance can be alleviated. We implement two specific approaches, the exponential and separable natural evolutionary strategies, for parameter optimization of PQCs and compare them against standard gradient descent. We apply them to two different problems of ground state energy estimation using variational quantum eigensolver (VQE) and state preparation with circuits of varying depth and length. We also introduce batch optimization for circuits with larger depth to extend the use of evolutionary strategies to a larger number of parameters. We achieve accuracy comparable to state-of-the-art optimization techniques in all the above cases with a lower number of circuit evaluations. Our empirical results indicate that one can use NES as a hybrid tool in tandem with other gradient-based methods for optimization of deep quantum circuits in regions with vanishing gradients.

Abhinav Anand, Jonathan Romero, Matthias Degroote et al.

The potential advantage of machine learning in quantum computers is a topic of intense discussion in the literature. Theoretical, numerical and experimental explorations will most likely be required to understand its power. There has been different algorithms proposed to exploit the probabilistic nature of variational quantum circuits for generative modelling. In this paper, we employ a hybrid architecture for quantum generative adversarial networks (QGANs) and study their robustness in the presence of noise. We devise a simple way of adding different types of noise to the quantum generator circuit, and numerically simulate the noisy hybrid quantum generative adversarial networks (HQGANs) to learn continuous probability distributions, and show that the performance of HQGANs remain unaffected. We also investigate the effect of different parameters on the training time to reduce the computational scaling of the algorithm and simplify its deployment on a quantum computer. We then perform the training on Rigetti's Aspen-4-2Q-A quantum processing unit, and present the results from the training. Our results pave the way for experimental exploration of different quantum machine learning algorithms on noisy intermediate scale quantum devices.

Abhishek Bansal, Abhinav Anand, Chiranjib Bhattacharyya

Understanding the representational power of Restricted Boltzmann Machines (RBMs) with multiple layers is an ill-understood problem and is an area of active research. Motivated from the approach of \emph{Inherent Structure formalism} (Stillinger & Weber, 1982), extensively used in analysing Spin Glasses, we propose a novel measure called \emph{Inherent Structure Capacity} (ISC), which characterizes the representation capacity of a fixed architecture RBM by the expected number of modes of distributions emanating from the RBM with parameters drawn from a prior distribution. Though ISC is intractable, we show that for a single layer RBM architecture ISC approaches a finite constant as number of hidden units are increased and to further improve the ISC, one needs to add a second layer. Furthermore, we introduce \emph{Lean} RBMs, which are multi-layer RBMs where each layer can have at-most $O(n)$ units with the number of visible units being n. We show that for every single layer RBM with $Ω(n^{2+r}), r \ge 0$, hidden units there exists a two-layered \emph{lean} RBM with $Θ(n^2)$ parameters with the same ISC, establishing that 2 layer RBMs can achieve the same representational power as single-layer RBMs but using far fewer number of parameters. To the best of our knowledge, this is the first result which quantitatively establishes the need for layering.

Avnish Chandra Suman, Saraswati Mishra, Abhinav Anand

In the last few years it has been seen that many software vendors have started delivering projects incrementally with very short release cycles. Best examples of success of this approach has been Ubuntu Operating system that has a 6 months release cycle and popular web browsers such as Google Chrome, Opera, Mozilla Firefox. However there is very little knowledge available to the project managers to validate the chosen release cycle length. We propose a decision support system that helps to validate and estimate release cycle length in the early development phase by assuming that release cycle length is directly affected by three factors, (i) choosing right requirements for current cycle, (ii) estimating proximal time for each requirement, (iii) requirement wise feedback from last iteration based on product reception, model accuracy and failed requirements. We have altered and used the EVOLVE technique proposed by G. Ruhe to select best requirements for current cycle and map it to time domain using UCP (Use Case Points) based estimation and feedback factors. The model has been evaluated on both in-house as well as industry projects.