Author name cluster

Lav R. Varshney

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

TMLR Journal 2026 Journal Article

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning

Raghav Singhal
Kaustubh Ponkshe
Rohit Vartak
Lav R. Varshney
Praneeth Vepakomma

Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates arising from traditional federated averaging of individual adapters. Existing solutions either incur prohibitively high communication cost that scales linearly with the number of clients or suffer from performance degradation due to limited expressivity. We introduce Fed-SB, a novel approach for federated fine-tuning of LLMs using LoRA-SB, a recently proposed low-rank adaptation method. LoRA-SB optimally aligns the optimization trajectory with the ideal low-rank full fine-tuning projection by learning a small square matrix ($R$) between adapters $B$ and $A$, keeping other components fixed. Direct averaging of $R$ guarantees exact updates, substantially reducing communication cost, which remains independent of the number of clients, and enables scalability. Fed-SB achieves state-of-the-art performance across commonsense reasoning, arithmetic reasoning, and language inference tasks while reducing communication costs by up to 230x. In private settings, Fed-SB further improves performance by (1) reducing trainable parameters, thereby lowering the noise required for differential privacy and (2) avoiding noise amplification introduced by other methods. Overall, Fed-SB offers a state-of-the-art, efficient, and scalable solution for both private and non-private federated fine-tuning. Our code is available publicly at: https://github.com/CERT-Lab/fed-sb.

PDF Details

TMLR Journal 2025 Journal Article

Cross-lingual Transfer in Programming Languages: An Extensive Empirical Study

Razan Baltaji
Saurabh Pujar
Martin Hirzel
Louis Mandel
Luca Buratti
Lav R. Varshney

Large language models (LLMs) have achieved state-of-the-art performance in various software engineering tasks, including error detection, clone detection, and code translation, primarily leveraging high-resource programming languages like Python and Java. However, many critical languages, such as COBOL, as well as emerging languages, such as Rust and Swift, remain low-resource due to limited openly available code. This scarcity hampers the training and effectiveness of LLMs for these languages, increasing software maintenance costs and stifling innovation. Addressing this gap, we investigate the potential of transfer learning to enhance LLM performance on low-resource programming languages by leveraging data from high-resource counterparts. Our extensive empirical study evaluates transferability across 10 to 41 programming languages and five key tasks: code generation, clone detection, code repair, solution domain classification, and error detection. Additionally, we develop a performance prediction model to guess the best source languages for a given target and task, and analyze the features that influence transfer performance. We further replicate a representative subset of experiments with a larger model to test the generalizability of our conclusions to contemporary large‑scale LLMs. Our findings demonstrate that cross-lingual transfer significantly outperforms zero-shot learning, with effectiveness varying based on both source and target languages. Languages such as Java and Go emerge as the best targets, while Kotlin and JavaScript are excellent sources. Furthermore, our model reliably predicts successful transfer sources by considering linguistic and dataset-specific features, offering practical guidance for data acquisition and model training. This work contributes to the development of LLM-driven tools for low-resource programming languages and provides insights into the characteristics that facilitate transfer across language pairs.

PDF Details

ICML Conference 2025 Conference Paper

ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks

Saurabh Jha
Rohan R. Arora
Yuji Watanabe
Takumi Yanagawa
Yinfang Chen
Jackson Clark
Bhavya
Mudit Verma

Realizing the vision of using AI agents to automate critical IT tasks depends on the ability to measure and understand effectiveness of proposed solutions. We introduce ITBench, a framework that offers a systematic methodology for benchmarking AI agents to address real-world IT automation tasks. Our initial release targets three key areas: Site Reliability Engineering (SRE), Compliance and Security Operations (CISO), and Financial Operations (FinOps). The design enables AI researchers to understand the challenges and opportunities of AI agents for IT automation with push-button workflows and interpretable metrics. IT-Bench includes an initial set of 102 real-world scenarios, which can be easily extended by community contributions. Our results show that agents powered by state-of-the-art models resolve only 11. 4% of SRE scenarios, 25. 2% of CISO scenarios, and 25. 8% of FinOps scenarios (excluding anomaly detection). For FinOps-specific anomaly detection (AD) scenarios, AI agents achieve an F1 score of 0. 35. We expect ITBench to be a key enabler of AI-driven IT automation that is correct, safe, and fast. IT-Bench, along with a leaderboard and sample agent implementations, is available at https: //github. com/ibm/itbench.

Details

TMLR Journal 2024 Journal Article

Efficient Model-Agnostic Multi-Group Equivariant Networks

Razan Baltaji
Sourya Basu
Lav R. Varshney

Constructing model-agnostic group equivariant networks, such as equitune (Basu et al., 2023b) and its generalizations (Kim et al., 2023), can be computationally expensive for large product groups. We address this problem by providing efficient model-agnostic equivariant designs for two related problems: one where the network has multiple inputs each with potentially different groups acting on them, and another where there is a single input but the group acting on it is a large product group. For the first design, we initially consider a linear model and characterize the entire equivariant space that satisfies this constraint. This characterization gives rise to a novel fusion layer between different channels that satisfies an invariance-symmetry (IS) constraint, which we call an IS layer. We then extend this design beyond linear models, similar to equitune, consisting of equivariant and IS layers. We also show that the IS layer is a universal approximator of invariant-symmetric functions. Inspired by the first design, we use the notion of the IS property to design a second efficient model-agnostic equivariant design for large product groups acting on a single input. For the first design, we provide experiments on multi-image classification where each view is transformed independently with transformations such as rotations. We find equivariant models are robust to such transformations and perform competitively otherwise. For the second design, we consider three applications: language compositionality on the SCAN dataset to product groups; fairness in natural language generation from GPT-2 to address intersectionality; and robust zero-shot image classification with CLIP. Overall, our methods are simple and general, competitive with equitune and its variants, while also being computationally more efficient.

PDF Details

JMLR Journal 2023 Journal Article

A Group-Theoretic Approach to Computational Abstraction: Symmetry-Driven Hierarchical Clustering

Haizi Yu
Igor Mineyev
Lav R. Varshney

Humans' abstraction ability plays a key role in concept learning and knowledge discovery. This theory paper presents the mathematical formulation for computationally emulating human-like abstractions---computational abstraction---and abstraction processes developed hierarchically from innate priors like symmetries. We study the nature of abstraction via a group-theoretic approach, formalizing and practically computing abstractions as symmetry-driven hierarchical clustering. Compared to data-driven clustering like k-means or agglomerative clustering (a chain), our abstraction model is data-free, feature-free, similarity-free, and globally hierarchical (a lattice). This paper also serves as a theoretical generalization of several existing works. These include generalizing Shannon's information lattice, specialized algorithms for certain symmetry-induced clusterings, as well as formalizing knowledge discovery applications such as learning music theory from scores and chemistry laws from molecules. We consider computational abstraction as a first step towards a principled and cognitive way of achieving human-level concept learning and knowledge discovery. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

NeurIPS Conference 2023 Conference Paper

Efficient Equivariant Transfer Learning from Pretrained Models

Sourya Basu
Pulkit Katdare
Prasanna Sattigeri
Vijil Chenthamarakshan
Katherine Driggs-Campbell
Payel Das
Lav R. Varshney

Efficient transfer learning algorithms are key to the success of foundation models on diverse downstream tasks even with limited data. Recent works of Basu et al. (2023) and Kaba et al. (2022) propose group averaging (equitune) and optimization-based methods, respectively, over features from group-transformed inputs to obtain equivariant outputs from non-equivariant neural networks. While Kaba et al. (2022) are only concerned with training from scratch, we find that equitune performs poorly on equivariant zero-shot tasks despite good finetuning results. We hypothesize that this is because pretrained models provide better quality features for certain transformations than others and simply averaging them is deleterious. Hence, we propose λ-equitune that averages the features using importance weights, λs. These weights are learned directly from the data using a small neural network, leading to excellent zero-shot and finetuned results that outperform equitune. Further, we prove that λ-equitune is equivariant and a universal approximator of equivariant functions. Additionally, we show that the method of Kaba et al. (2022) used with appropriate loss functions, which we call equizero, also gives excellent zero-shot and finetuned performance. Both equitune and equizero are special cases of λ- equitune. To show the simplicity and generality of our method, we validate on a wide range of diverse applications and models such as 1) image classification using CLIP, 2) deep Q-learning, 3) fairness in natural language generation (NLG), 4) compositional generalization in languages, and 5) image classification using pretrained CNNs such as Resnet and Alexnet.

PDF Details

AAAI Conference 2023 Conference Paper

Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models

Sourya Basu
Prasanna Sattigeri
Karthikeyan Natesan Ramamurthy
Vijil Chenthamarakshan
Kush R. Varshney
Lav R. Varshney
Payel Das

We introduce equi-tuning, a novel fine-tuning method that transforms (potentially non-equivariant) pretrained models into group equivariant models while incurring minimum L_2 loss between the feature representations of the pretrained and the equivariant models. Large pretrained models can be equi-tuned for different groups to satisfy the needs of various downstream tasks. Equi-tuned models benefit from both group equivariance as an inductive bias and semantic priors from pretrained models. We provide applications of equi-tuning on three different tasks: image classification, compositional generalization in language, and fairness in natural language generation (NLG). We also provide a novel group-theoretic definition for fairness in NLG. The effectiveness of this definition is shown by testing it against a standard empirical method of fairness in NLG. We provide experimental results for equi-tuning using a variety of pretrained models: Alexnet, Resnet, VGG, and Densenet for image classification; RNNs, GRUs, and LSTMs for compositional generalization; and GPT2 for fairness in NLG. We test these models on benchmark datasets across all considered tasks to show the generality and effectiveness of the proposed method.

PDF Details DOI

JAIR Journal 2023 Journal Article

Information Lattice Learning

Haizi Yu
James A. Evans
Lav R. Varshney

We propose Information Lattice Learning (ILL) as a general framework to learn rules of a signal (e.g., an image or a probability distribution). In our definition, a rule is a coarsened signal used to help us gain one interpretable insight about the original signal. To make full sense of what might govern the signal’s intrinsic structure, we seek multiple disentangled rules arranged in a hierarchy, called a lattice. Compared to representation/rule-learning models optimized for a specific task (e.g., classification), ILL focuses on explainability: it is designed to mimic human experiential learning and discover rules akin to those humans can distill and comprehend. This paper details the math and algorithms of ILL, and illustrates how it addresses the fundamental question “what makes X an X” by creating rule-based explanations designed to help humans understand. Our focus is on explaining X rather than (re)generating it. We present applications in knowledge discovery, using ILL to distill music theory from scores and chemical laws from molecules and further revealing connections between them. We show ILL’s efficacy and interpretability on benchmarks and assessments, as well as a demonstration of ILL-enhanced classifiers achieving human-level digit recognition using only one or a few MNIST training examples (1–10 per class).

PDF Details DOI

AAAI Conference 2023 Conference Paper

Learning Optimal Features via Partial Invariance

Moulik Choraria
Ibtihal Ferwana
Ankur Mani
Lav R. Varshney

Learning models that are robust to distribution shifts is a key concern in the context of their real-life applicability. Invariant Risk Minimization (IRM) is a popular framework that aims to learn robust models from multiple environments. The success of IRM requires an important assumption: the underlying causal mechanisms/features remain invariant across environments. When not satisfied, we show that IRM can over-constrain the predictor and to remedy this, we propose a relaxation via partial invariance. In this work, we theoretically highlight the sub-optimality of IRM and then demonstrate how learning from a partition of training domains can help improve invariant models. Several experiments, conducted both in linear settings as well as with deep neural networks on tasks over both language and image data, allow us to verify our conclusions.

PDF Details DOI

TMLR Journal 2022 Journal Article

Nonstationary Reinforcement Learning with Linear Function Approximation

Huozhi Zhou
Jinglin Chen
Lav R. Varshney
Ashish Jagmohan

We consider reinforcement learning (RL) in episodic Markov decision processes (MDPs) with linear function approximation under drifting environment. Specifically, both the reward and state transition functions can evolve over time but their total variations do not exceed a \textit{variation budget}. We first develop $\texttt{LSVI-UCB-Restart}$ algorithm, an optimistic modification of least-squares value iteration with periodic restart, and bound its dynamic regret when variation budgets are known. Then we propose a parameter-free algorithm \texttt{Ada-LSVI-UCB-Restart} that extends to unknown variation budgets. We also derive the first minimax dynamic regret lower bound for nonstationary linear MDPs and as a byproduct establish a minimax regret lower bound for linear MDPs unsolved by Jin et al. (2020). Finally, we provide numerical experiments to demonstrate the effectiveness of our proposed algorithms.

PDF Details

AAAI Conference 2021 Conference Paper

Adversarial Linear Contextual Bandits with Graph-Structured Side Observations

Lingda Wang
Bingcong Li
Huozhi Zhou
Georgios B. Giannakis
Lav R. Varshney
Zhizhen Zhao

This paper studies the adversarial graphical contextual bandits, a variant of adversarial multi-armed bandits that leverage two categories of the most common side information: contexts and side observations. In this setting, a learning agent repeatedly chooses from a set of K actions after being presented with a d-dimensional context vector. The agent not only incurs and observes the loss of the chosen action, but also observes the losses of its neighboring actions in the observation structures, which are encoded as a series of feedback graphs. This setting models a variety of applications in social networks, where both contexts and graph-structured side observations are available. Two efficient algorithms are developed based on EXP3. Under mild conditions, our analysis shows that for undirected feedback graphs the first algorithm, EXP3-LGC-U, achieves a sub-linear regret with respect to the time horizon and the average independence number of the feedback graphs. A slightly weaker result is presented for the directed graph setting as well. The second algorithm, EXP3-LGC-IX, is developed for a special class of problems, for which the regret is the same for both directed as well as undirected feedback graphs. Numerical tests corroborate the efficiency of proposed algorithms.

PDF Details

ICLR Conference 2021 Conference Paper

BERTology Meets Biology: Interpreting Attention in Protein Language Models

Jesse Vig
Ali Madani
Lav R. Varshney
Caiming Xiong
Richard Socher
Nazneen Rajani

Transformer architectures have proven to learn useful representations for protein classification and generation tasks. However, these representations present challenges in interpretability. In this work, we demonstrate a set of methods for analyzing protein Transformer models through the lens of attention. We show that attention: (1) captures the folding structure of proteins, connecting amino acids that are far apart in the underlying sequence, but spatially close in the three-dimensional structure, (2) targets binding sites, a key functional component of proteins, and (3) focuses on progressively more complex biophysical properties with increasing layer depth. We find this behavior to be consistent across three Transformer architectures (BERT, ALBERT, XLNet) and two distinct protein datasets. We also present a three-dimensional visualization of the interaction between attention and protein structure. Code for visualization and analysis is available at https://github.com/salesforce/provis.

Details

NeurIPS Conference 2021 Conference Paper

Evaluating State-of-the-Art Classification Models Against Bayes Optimality

Ryan Theisen
Huan Wang
Lav R. Varshney
Caiming Xiong
Richard Socher

Evaluating the inherent difficulty of a given data-driven classification problem is important for establishing absolute benchmarks and evaluating progress in the field. To this end, a natural quantity to consider is the \emph{Bayes error}, which measures the optimal classification error theoretically achievable for a given data distribution. While generally an intractable quantity, we show that we can compute the exact Bayes error of generative models learned using normalizing flows. Our technique relies on a fundamental result, which states that the Bayes error is invariant under invertible transformation. Therefore, we can compute the exact Bayes error of the learned flow models by computing it for Gaussian base distributions, which can be done efficiently using Holmes-Diaconis-Ross integration. Moreover, we show that by varying the temperature of the learned flow models, we can generate synthetic datasets that closely resemble standard benchmark datasets, but with almost any desired Bayes error. We use our approach to conduct a thorough investigation of state-of-the-art classification models, and find that in some --- but not all --- cases, these models are capable of obtaining accuracy very near optimal. Finally, we use our method to evaluate the intrinsic "hardness" of standard benchmark datasets.

PDF Details

ICLR Conference 2021 Conference Paper

Mirostat: a Neural Text decoding Algorithm that directly controls perplexity

Sourya Basu
Govardana Sachitanandam Ramachandran
Nitish Shirish Keskar
Lav R. Varshney

Neural text decoding algorithms strongly influence the quality of texts generated using language models, but popular algorithms like top-k, top-p (nucleus), and temperature-based sampling may yield texts that have objectionable repetition or incoherence. Although these methods generate high-quality text after ad hoc parameter tuning that depends on the language model and the length of generated text, not much is known about the control they provide over the statistics of the output. This is important, however, since recent reports show that humans prefer when perplexity is neither too much nor too little and since we experimentally show that cross-entropy (log of perplexity) has a near-linear relation with repetition. First, we provide a theoretical analysis of perplexity in top-k, top-p, and temperature sampling, under Zipfian statistics. Then, we use this analysis to design a feedback-based adaptive top-k text decoding algorithm called mirostat that generates text (of any length) with a predetermined target value of perplexity without any tuning. Experiments show that for low values of k and p, perplexity drops significantly with generated text length and leads to excessive repetitions (the boredom trap). Contrarily, for large values of k and p, perplexity increases with generated text length and leads to incoherence (confusion trap). Mirostat avoids both traps. Specifically, we show that setting target perplexity value beyond a threshold yields negligible sentence-level repetitions. Experiments with human raters for fluency, coherence, and quality further verify our findings.

Details