arXiv subjects

Anup Rao

Publications and source records attributed to Anup Rao.

At least 19 recordsLinked to original sources

arXiv2026

AdvantageFlow: Advantage-Weighted Least Squares for RL in Flow Models

We introduce AdvantageFlow, a forward-process reinforcement learning algorithm for rectified flow models. Unlike Flow-GRPO, which optimizes the reverse process, we optimize an advantage-weighted forward-process prediction loss. This optimization problem is unstable when advantages are negative and the loss becomes non-convex. We stabilize it by rollout policy regularization, which reduces variance and arises from fitting a local reward-improving target distribution. We evaluate AdvantageFlow on image generation tasks with Stable Diffusion 3.5 Medium. It outperforms both Flow-GRPO and a state-of-the-art forward-process RL baseline based on negative-aware fine-tuning.

cs.LG↗

arXiv2025

Learning to Reason in LLMs by Expectation Maximization

Large language models (LLMs) solve reasoning problems by first generating a rationale and then answering. We formalize reasoning as a latent variable model and derive a reward-based filtered expectation-maximization (FEM) objective for learning to reason. This view connects EM and modern reward-based optimization, and shows that the main challenge lies in designing a sampling distribution of rationales that justify correct answers. We instantiate and compare three sampling schemes: rejection sampling with a budget, self-taught reasoner (STaR), and prompt posterior sampling (PPS), which only keeps the rationalization stage of STaR that conditions on the correct answer in the prompt. We experiment with LLM-as-a-judge calibration and summarization from feedback tasks, where conditioning on the correct answer provides a strong guidance for generating rationales. Our experiments show the efficacy of PPS over other sampling schemes, and that the sampling scheme can have a significant impact on performance.

cs.LG↗

arXiv2025

ML-Tool-Bench: Tool-Augmented Planning for ML Tasks

The development of autonomous machine learning (ML) agents capable of end-to-end data science workflows represents a significant frontier in artificial intelligence. These agents must orchestrate complex sequences of data analysis, feature engineering, model selection, and hyperparameter optimization, tasks that require sophisticated planning and iteration. While recent work on building ML agents has explored using large language models (LLMs) for direct code generation, tool-augmented approaches offer greater modularity and reliability. However, existing tool-use benchmarks focus primarily on task-specific tool selection or argument extraction for tool invocation, failing to evaluate the sophisticated planning capabilities required for ML Agents. In this work, we introduce a comprehensive benchmark for evaluating tool-augmented ML agents using a curated set of 61 specialized tools and 15 tabular ML challenges from Kaggle. Our benchmark goes beyond traditional tool-use evaluation by incorporating an in-memory named object management, allowing agents to flexibly name, save, and retrieve intermediate results throughout the workflows. We demonstrate that standard ReAct-style approaches struggle to generate valid tool sequences for complex ML pipelines, and that tree search methods with LLM-based evaluation underperform due to inconsistent state scoring. To address these limitations, we propose two simple approaches: 1) using shaped deterministic rewards with structured textual feedback, and 2) decomposing the original problem into a sequence of sub-tasks, which significantly improves trajectory validity and task performance. Using GPT-4o, our approach improves over ReAct by 16.52 percentile positions, taking the median across all Kaggle challenges. We believe our work provides a foundation for developing more capable tool-augmented planning ML agents.

cs.LG↗

arXiv2025

The Story of Sunflowers

Sunflowers, or $\Delta$-systems, are a fundamental concept in combinatorics introduced by Erd\H{o}s and Rado in their paper: {\em Intersection theorems for systems of sets}, J. Lond. Math. Soc. (1) {\bf 35} (1960), 85--90. A sunflower is a collection of sets where all pairs have the same intersection. This paper explores the wide-ranging applications of sunflowers in computer science and combinatorics. We discuss recent progress towards the sunflower conjecture and present a short elementary proof of the best known bounds for the robust sunflower lemma.

math.CO↗

arXiv2025

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practical approach to offline RL with large language models (LLMs). We recast the problem as reward-weighted fine-tuning, which can be solved using similar techniques to supervised fine-tuning (SFT). To showcase the value of our approach, we apply it to learning short-horizon question-answering policies of a fixed length, where the agent reasons about potential answers or asks clarifying questions. Our work stands in a stark contrast to state-of-the-art methods in this domain, based on SFT and direct preference optimization, which have additional hyper-parameters and do not directly optimize for rewards. We compare to them empirically, and report major gains in both optimized rewards and language quality.

cs.CL↗

arXiv2025

Evaluation and Incident Prevention in an Enterprise AI Assistant

Enterprise AI Assistants are increasingly deployed in domains where accuracy is paramount, making each erroneous output a potentially significant incident. This paper presents a comprehensive framework for monitoring, benchmarking, and continuously improving such complex, multi-component systems under active development by multiple teams. Our approach encompasses three key elements: (1) a hierarchical ``severity'' framework for incident detection that identifies and categorizes errors while attributing component-specific error rates, facilitating targeted improvements; (2) a scalable and principled methodology for benchmark construction, evaluation, and deployment, designed to accommodate multiple development teams, mitigate overfitting risks, and assess the downstream impact of system modifications; and (3) a continual improvement strategy leveraging multidimensional evaluation, enabling the identification and implementation of diverse enhancement opportunities. By adopting this holistic framework, organizations can systematically enhance the reliability and performance of their AI Assistants, ensuring their efficacy in critical enterprise environments. We conclude by discussing how this multifaceted evaluation approach opens avenues for various classes of enhancements, paving the way for more robust and trustworthy AI systems.

cs.AI↗

arXiv2024

An XOR Lemma for Deterministic Communication Complexity

We prove a lower bound on the communication complexity of computing the $n$-fold xor of an arbitrary function $f$, in terms of the communication complexity and rank of $f$. We prove that $D(f^{\oplus n}) \geq n \cdot \Big(\frac{\Omega(D(f))}{\log \mathsf{rk}(f)} -\log \mathsf{rk}(f)\Big )$, where here $D(f), D(f^{\oplus n})$ represent the deterministic communication complexity, and $\mathsf{rk}(f)$ is the rank of $f$. Our methods involve a new way to use information theory to reason about deterministic communication complexity.

cs.CC↗

arXiv2024

Hallucination Diversity-Aware Active Learning for Text Summarization

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations.

cs.CL↗

arXiv2023

XOR Lemmas for Communication via Marginal Information

We define the $\textit{marginal information}$ of a communication protocol, and use it to prove XOR lemmas for communication complexity. We show that if every $C$-bit protocol has bounded advantage for computing a Boolean function $f$, then every $\tilde \Omega(C \sqrt{n})$-bit protocol has advantage $\exp(-\Omega(n))$ for computing the $n$-fold xor $f^{\oplus n}$. We prove exponentially small bounds in the average case setting, and near optimal bounds for product distributions and for bounded-round protocols.

cs.CC↗

arXiv2023

Decentralized Personalized Online Federated Learning

Vanilla federated learning does not support learning in an online environment, learning a personalized model on each client, and learning in a decentralized setting. There are existing methods extending federated learning in each of the three aspects. However, some important applications on enterprise edge servers (e.g. online item recommendation at global scale) involve the three aspects at the same time. Therefore, we propose a new learning setting \textit{Decentralized Personalized Online Federated Learning} that considers all the three aspects at the same time. In this new setting for learning, the first technical challenge is how to aggregate the shared model parameters from neighboring clients to obtain a personalized local model with good performance on each client. We propose to directly learn an aggregation by optimizing the performance of the local model with respect to the aggregation weights. This not only improves personalization of each local model but also helps the local model adapting to potential data shift by intelligently incorporating the right amount of information from its neighbors. The second challenge is how to select the neighbors for each client. We propose a peer selection method based on the learned aggregation weights enabling each client to select the most helpful neighbors and reduce communication cost at the same time. We verify the effectiveness and robustness of our proposed method on three real-world item recommendation datasets and one air quality prediction dataset.

cs.LG↗

arXiv2023

Dynamic Vector Bin Packing for Online Resource Allocation in the Cloud

Several cloud-based applications, such as cloud gaming, rent servers to execute jobs which arrive in an online fashion. Each job has a resource demand and must be dispatched to a cloud server which has enough resources to execute the job, which departs after its completion. Under the `pay-as-you-go' billing model, the server rental cost is proportional to the total time that servers are actively running jobs. The problem of efficiently allocating a sequence of online jobs to servers without exceeding the resource capacity of any server while minimizing total server usage time can be modelled as a variant of the dynamic bin packing problem (DBP), called MinUsageTime DBP. In this work, we initiate the study of the problem with multi-dimensional resource demands (e.g. CPU/GPU usage, memory requirement, bandwidth usage, etc.), called MinUsageTime Dynamic Vector Bin Packing (DVBP). We study the competitive ratio (CR) of Any Fit packing algorithms for this problem. We show almost-tight bounds on the CR of three specific Any Fit packing algorithms, namely First Fit, Next Fit, and Move To Front. We prove that the CR of Move To Front is at most $(2μ+1)d +1$, where $μ$ is the ratio of the max/min item durations. For $d=1$, this significantly improves the previously known upper bound of $6μ+7$ (Kamali & Lopez-Ortiz, 2015). We then prove the CR of First Fit and Next Fit are bounded by $(μ+2)d+1$ and $2μd+1$, respectively. Next, we prove a lower bound of $(μ+1)d$ on the CR of any Any Fit packing algorithm, an improved lower bound of $2μd$ for Next Fit, and a lower bound of $2μ$ for Move To Front in the 1-D case. All our bounds improve or match the best-known bounds for the 1-D case. Finally, we experimentally study the average-case performance of these algorithms on randomly generated synthetic data, and observe that Move To Front outperforms other Any Fit packing algorithms.

cs.DS↗

arXiv2023

Elastic Cash

Elastic Cash is a new decentralized mechanism for regulating the money supply. The mechanism operates by modifying the supply so that an interest rate determined by a public market is kept approximately fixed. It can be incorporated into the conventional monetary system to improve the elasticity of the US Dollar, and it can be used to design new elastic cryptocurrencies that remain decentralized.

q-fin.GN↗

arXiv2022

Model Selection in Contextual Stochastic Bandit Problems

We study bandit model selection in stochastic environments. Our approach relies on a meta-algorithm that selects between candidate base algorithms. We develop a meta-algorithm-base algorithm abstraction that can work with general classes of base algorithms and different type of adversarial meta-algorithms. Our methods rely on a novel and generic smoothing transformation for bandit algorithms that permits us to obtain optimal $O(\sqrt{T})$ model selection guarantees for stochastic contextual bandit problems as long as the optimal base algorithm satisfies a high probability regret guarantee. We show through a lower bound that even when one of the base algorithms has $O(\log T)$ regret, in general it is impossible to get better than $Ω(\sqrt{T})$ regret in model selection, even asymptotically. Using our techniques, we address model selection in a variety of problems such as misspecified linear contextual bandits, linear bandit with unknown dimension and reinforcement learning with unknown feature maps. Our algorithm requires the knowledge of the optimal base regret to adjust the meta-algorithm learning rate. We show that without such prior knowledge any meta-algorithm can suffer a regret larger than the optimal base regret.

cs.LG↗

arXiv2022

Sample Constrained Treatment Effect Estimation

Treatment effect estimation is a fundamental problem in causal inference. We focus on designing efficient randomized controlled trials, to accurately estimate the effect of some treatment on a population of $n$ individuals. In particular, we study sample-constrained treatment effect estimation, where we must select a subset of $s \ll n$ individuals from the population to experiment on. This subset must be further partitioned into treatment and control groups. Algorithms for partitioning the entire population into treatment and control groups, or for choosing a single representative subset, have been well-studied. The key challenge in our setting is jointly choosing a representative subset and a partition for that set. We focus on both individual and average treatment effect estimation, under a linear effects model. We give provably efficient experimental designs and corresponding estimators, by identifying connections to discrepancy minimization and leverage-score-based sampling used in randomized numerical linear algebra. Our theoretical results obtain a smooth transition to known guarantees when $s$ equals the population size. We also empirically demonstrate the performance of our algorithms.

cs.LG↗

arXiv2022

Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings

Many models for undirected graphs are based on factorizing the graph's adjacency matrix; these models find a vector representation of each node such that the predicted probability of a link between two nodes increases with the similarity (dot product) of their associated vectors. Recent work has shown that these models are unable to capture key structures in real-world graphs, particularly heterophilous structures, wherein links occur between dissimilar nodes. In contrast, a factorization with two vectors per node, based on logistic principal components analysis (LPCA), has been proven not only to represent such structures, but also to provide exact low-rank factorization of any graph with bounded max degree. However, this bound has limited applicability to real-world networks, which often have power law degree distributions with high max degree. Further, the LPCA model lacks interpretability since its asymmetric factorization does not reflect the undirectedness of the graph. We address these issues in two ways. First, we prove a new bound for the LPCA model in terms of arboricity rather than max degree; this greatly increases the bound's applicability to many sparse real-world networks. Second, we propose an alternative graph model whose factorization is symmetric and nonnegative, which allows for link predictions to be interpreted in terms of node clusters. We show that the bounds for exact representation in the LPCA model extend to our new model. On the empirical side, our model is optimized effectively on real-world graphs with gradient descent on a cross-entropy loss. We demonstrate its effectiveness on a variety of foundational tasks, such as community detection and link prediction.

cs.LG↗

arXiv2022

Online Balanced Experimental Design

e consider the experimental design problem in an online environment, an important practical task for reducing the variance of estimates in randomized experiments which allows for greater precision, and in turn, improved decision making. In this work, we present algorithms that build on recent advances in online discrepancy minimization which accommodate both arbitrary treatment probabilities and multiple treatments. The proposed algorithms are computational efficient, minimize covariate imbalance, and include randomization which enables robustness to misspecification. We provide worst case bounds on the expected mean squared error of the causal estimate and show that the proposed estimator is no worse than an implicit ridge regression, which are within a logarithmic factor of the best known results for offline experimental design. We conclude with a detailed simulation study showing favorable results relative to complete randomization as well as to offline methods for experimental design with time complexities exceeding our algorithm.

stat.ME↗

arXiv2022

A Criterion for Decoding on the BSC

We present an approach to showing that a linear code is resilient to random errors. We use this approach to obtain decoding results for both transitive codes and Reed-Muller codes. We give three kinds of results about linear codes in general, and transitive linear codes in particular. 1) We give a tight bound on the weight distribution of every transitive linear code $C \subseteq \mathbb{F}_2^N$: $\Pr_{c \in C}[|c| = \alpha N] \leq 2^{-(1-h(\alpha)) \mathsf{dim}(C)}$. 2) We give a criterion that certifies that a linear code $C$ can be decoded on the binary symmetric channel. Let $K_s(x)$ denote the Krawtchouk polynomial of degree $s$, and let $C^\perp$ denote the dual code of $C$. We show that bounds on $\mathbb{E}_{c \in C^{\perp}}[ K_{\epsilon N}(|c|)^2]$ imply that $C$ recovers from errors on the binary symmetric channel with parameter $\epsilon$. Weaker bounds can be used to obtain list-decoding results using similar methods. One consequence of our criterion is that whenever the weight distribution of $C^\perp$ is sufficiently close to the binomial distribution in some interval around $\frac{N}{2}$, $C$ is resilient to $\epsilon$-errors. 3) We combine known estimates for the Krawtchouk polynomials with our weight bound for transitive codes, and with known weight bounds for Reed-Muller codes, to obtain list-decoding results for both these families of codes. In some regimes, our bounds for Reed-Muller codes achieve the information-theoretic optimal trade-off between rate and list size.

cs.IT↗

arXiv2022

Electra: Conditional Generative Model based Predicate-Aware Query Approximation

The goal of Approximate Query Processing (AQP) is to provide very fast but "accurate enough" results for costly aggregate queries thereby improving user experience in interactive exploration of large datasets. Recently proposed Machine-Learning based AQP techniques can provide very low latency as query execution only involves model inference as compared to traditional query processing on database clusters. However, with increase in the number of filtering predicates(WHERE clauses), the approximation error significantly increases for these methods. Analysts often use queries with a large number of predicates for insights discovery. Thus, maintaining low approximation error is important to prevent analysts from drawing misleading conclusions. In this paper, we propose ELECTRA, a predicate-aware AQP system that can answer analytics-style queries with a large number of predicates with much smaller approximation errors. ELECTRA uses a conditional generative model that learns the conditional distribution of the data and at runtime generates a small (~1000 rows) but representative sample, on which the query is executed to compute the approximate result. Our evaluations with four different baselines on three real-world datasets show that ELECTRA provides lower AQP error for large number of predicates compared to baselines.

cs.DB↗