Search Results for author:
Found 28 papers, 1 papers with code
Robust Learning of Diverse Code Edits
Software engineering activities frequently involve edits to existing code.
Plan$\times$RAG: Planning-guided Retrieval Augmented Generation
We introduce Planning-guided Retrieval Augmented Generation (Plan$\times$RAG), a novel framework that augments the \emph{retrieve-then-reason} paradigm of existing RAG frameworks to \emph{plan-then-retrieve}.
ASTRA: Accurate and Scalable ANNS-based Training of Extreme Classifiers
State-of-the-art XC techniques that demonstrate high accuracies (e. g., DEXML, Ren\'ee, DEXA) on standard datasets have per-epoch training time that scales as $O(L)$ or employ expensive negative sampling strategies, which are prohibitive in XC scenarios.
CROSS-JEM: Accurate and Efficient Cross-encoders for Short-text Ranking Tasks
In response, we propose Cross-encoders with Joint Efficient Modeling (CROSS-JEM), a novel ranking approach that enables transformer-based models to jointly score multiple items for a query, maximizing parameter utilization.
MASAI: Modular Architecture for Software-engineering AI Agents
A common method to solve complex problems in software engineering, is to divide the problem into multiple sub-problems.
Task Facet Learning: A Structured Approach to Prompt Optimization
Given a task in the form of a basic description and its training examples, prompt optimization is the problem of synthesizing the given information into a text prompt for a large language model (LLM).
Provably Robust DPO: Aligning Language Models with Noisy Feedback
Our experiments on IMDb sentiment generation and Anthropic's helpful-harmless dataset show that rDPO is robust to noise in preference labels compared to vanilla DPO and other heuristics proposed by practitioners.
NoFunEval: Funny How Code LMs Falter on Requirements Beyond Functional Correctness
We propose a new benchmark NoFunEval to evaluate code LMs on non-functional requirements and simple classification instances for both functional and non-functional requirements.
GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval
Given a query and a document corpus, the information retrieval (IR) task is to output a ranked list of relevant documents.
Differentially Private Reward Estimation with Preference Feedback
Within a standard minimax estimation framework, we provide tight upper and lower bounds on the error in estimating $\theta^*$ under both local and central models of DP.
Frustrated with Code Quality Issues? LLMs can Help!
We present a tool, CORE (short for COde REvisions), architected using a pair of LLMs organized as a duo comprised of a proposer and a ranker.
Simulating Network Paths with Recurrent Buffering Units
Simulating physical network paths (e. g., Internet) is a cornerstone research problem in the emerging sub-field of AI-for-networking.
Optimal Regret Algorithm for Pseudo-1d Bandit Convex Optimization
We study online learning with bandit feedback (i. e. learner has access to only zeroth-order oracle) where cost/reward functions $\f_t$ admit a "pseudo-1d" structure, i. e. $\f_t(\w) = \loss_t(\pred_t(\w))$ where the output of $\pred_t$ is one-dimensional.
Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
Decision trees provide a rich family of highly non-linear but efficient models, due to which they continue to be the go-to family of predictive models by practitioners across domains.
Oasis: ILP-Guided Synthesis of Loop Invariants
Automated synthesis of inductive invariants is an important problem in software verification.
Programming by Rewards
The goal of the synthesizer is to synthesize a "decision function" $f$ which transforms the features to a decision value for the black-box component so as to maximize the expected reward $E[r \circ f (x)]$ for executing decisions $f(x)$ for various values of $x$.
On Scaling Data-Driven Loop Invariant Inference
Automated synthesis of inductive invariants is an important problem in software verification.
Leveraging Distributional Semantics for Multi-Label Learning
Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and paragraph/document embedding methods commonly used for learning representations of text data.
Consistency Analysis for Binary Classification Revisited
Statistical learning theory is at an inflection point enabled by recent advances in understanding and optimizing a wide range of metrics.
Active Heteroscedastic Regression
In this work, we consider a theoretical analysis of the label requirement of active learning for regression under a heteroscedastic noise model, where the noise depends on the instance.
Regret Bounds for Non-decomposable Metrics with Missing Labels
We consider the problem of recommending relevant labels (items) for a given data point (user).
Learning from Binary Labels with Instance-Dependent Corruption
Suppose we have a sample of instances paired with binary labels corrupted by arbitrary instance- and label-dependent noise.
Consistent Multilabel Classification
In particular, we show that for multilabel metrics constructed as instance-, micro- and macro-averages, the population optimal classifier can be decomposed into binary classifiers based on the marginal instance-conditional distribution of each label, with a weak association between labels via the threshold.
Predtron: A Family of Online Algorithms for General Prediction Problems
We offer a general framework to derive mistake driven online algorithms and associated loss bounds.
Optimal Decision-Theoretic Classification Using Non-Decomposable Performance Metrics
We provide a general theoretical analysis of expected out-of-sample utility, also referred to as decision-theoretic classification, for non-decomposable binary classification metrics such as F-measure and Jaccard coefficient.
Consistent Binary Classification with Generalized Performance Metrics
We consider a fairly large family of performance metrics given by ratios of linear combinations of the four fundamental population quantities.
PU Learning for Matrix Completion
For the first case, we propose a "shifted matrix completion" method that recovers M using only a subset of indices corresponding to ones, while for the second case, we propose a "biased matrix completion" method that recovers the (thresholded) binary matrix.
Learning with Noisy Labels
In this paper, we theoretically study the problem of binary classification in the presence of random classification noise --- the learner, instead of seeing the true labels, sees labels that have independently been flipped with some small probability.
