Author name cluster

Kartik Gupta

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.

7 papers

2 author rows

ICML Conference 2025 Conference Paper

Can We Predict Performance of Large Models across Vision-Language Tasks?

Qinyu Zhao
Ming Xu 0015
Kartik Gupta
Akshay Asthana
Liang Zheng 0001
Stephen Gould

Evaluating large vision-language models (LVLMs) is very expensive, due to high computational cost and the wide variety of tasks. The good news is that if we already have some observed performance scores, we may be able to infer unknown ones. In this study, we propose a new framework for predicting unknown performance scores based on observed ones from other LVLMs or tasks. We first formulate the performance prediction as a matrix completion task. Specifically, we construct a sparse performance matrix $\boldsymbol{R}$, where each entry $R_{mn}$ represents the performance score of the $m$-th model on the $n$-th dataset. By applying probabilistic matrix factorization (PMF) with Markov chain Monte Carlo (MCMC), we can complete the performance matrix, i. e. , predict unknown scores. Additionally, we estimate the uncertainty of performance prediction based on MCMC. Practitioners can evaluate their models on untested tasks with higher uncertainty first, which quickly reduces the prediction errors. We further introduce several improvements to enhance PMF for scenarios with sparse observed performance scores. Our experiments demonstrate the accuracy of PMF in predicting unknown scores, the reliability of uncertainty estimates in ordering evaluations, and the effectiveness of our enhancements for handling sparse data. Our code is available at https: //github. com/Qinyu-Allen-Zhao/CrossPred-LVLM.

Details

ICLR Conference 2024 Conference Paper

Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection

Qinyu Zhao
Ming Xu 0015
Kartik Gupta
Akshay Asthana
Liang Zheng 0001
Stephen Gould

Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection. These approaches manipulate the feature representation, typically from the penultimate layer of a pre-trained deep learning model, so as to better differentiate between in-distribution (ID) and OOD samples. However, existing feature-shaping methods usually employ rules manually designed for specific model architectures and OOD datasets, which consequently limit their generalization ability. To address this gap, we first formulate an abstract optimization framework for studying feature-shaping methods. We then propose a concrete reduction of the framework with a simple piecewise constant shaping function and show that existing feature-shaping methods approximate the optimal solution to the concrete optimization problem. Further, assuming that OOD data is inaccessible, we propose a formulation that yields a closed-form solution for the piecewise constant shaping function, utilizing solely the ID data. Through extensive experiments, we show that the feature-shaping function optimized by our method improves the generalization ability of OOD detection across a large variety of datasets and model architectures. Our code is available at https://github.com/Qinyu-Allen-Zhao/OptFSOOD.

Details

TMLR Journal 2023 Journal Article

Quantization Robust Federated Learning for Efficient Inference on Heterogeneous Devices

Kartik Gupta
Marios Fournarakis
Matthias Reisser
Christos Louizos
Markus Nagel

Federated Learning (FL) is a machine learning paradigm to distributively learn machine learning models from decentralized data that remains on-device. Despite the success of standard Federated optimization methods, such as Federated Averaging (FedAvg) in FL, the energy demands and hardware induced constraints for on-device learning have not been considered sufficiently in the literature. Specifically, an essential demand for on-device learning is to enable trained models to be quantized to various bit-widths based on the energy needs and heterogeneous hardware designs across the federation. In this work, we introduce multiple variants of federated averaging algorithm that train neural networks robust to quantization. Such networks can be quantized to various bit-widths with only limited reduction in full precision model accuracy. We perform extensive experiments on standard FL benchmarks to evaluate our proposed FedAvg variants for quantization robustness and provide a convergence analysis for our Quantization-Aware variants in FL. Our results demonstrate that integrating quantization robustness results in FL models that are significantly more robust to different bit-widths during quantized on-device inference.

PDF Details

AAAI Conference 2022 Conference Paper

Improved Gradient-Based Adversarial Attacks for Quantized Networks

Kartik Gupta
Thalaiyasingam Ajanthan

Neural network quantization has become increasingly popular due to efficient memory consumption and faster computation resulting from bitwise operations on the quantized networks. Even though they exhibit excellent generalization capabilities, their robustness properties are not well-understood. In this work, we systematically study the robustness of quantized networks against gradient based adversarial attacks and demonstrate that these quantized models suffer from gradient vanishing issues and show a fake sense of robustness. By attributing gradient vanishing to poor forward-backward signal propagation in the trained network, we introduce a simple temperature scaling approach to mitigate this issue while preserving the decision boundary. Despite being a simple modification to existing gradient based adversarial attacks, experiments on multiple image classification datasets with multiple network architectures demonstrate that our temperature scaled attacks obtain near-perfect success rate on quantized networks while outperforming original attacks on adversarially trained models as well as floating-point networks.

PDF Details

ICLR Conference 2021 Conference Paper

Calibration of Neural Networks using Splines

Kartik Gupta
Amir Rahimi
Thalaiyasingam Ajanthan
Thomas Mensink
Cristian Sminchisescu
Richard I. Hartley

Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities. Measuring calibration error amounts to comparing two empirical distributions. In this work, we introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test in which the main idea is to compare the respective cumulative probability distributions. From this, by approximating the empirical cumulative distribution using a differentiable function via splines, we obtain a recalibration function, which maps the network outputs to actual (calibrated) class assignment probabilities. The spline-fitting is performed using a held-out calibration set and the obtained recalibration function is evaluated on an unseen test set. We tested our method against existing calibration approaches on various image classification datasets and our spline-based recalibration approach consistently outperforms existing methods on KS error as well as other commonly used calibration measures. Code is available online at https://github.com/kartikgupta-at-anu/spline-calibration.

Details

IROS Conference 2019 Conference Paper

Near-contact grasping strategies from awkward poses: When simply closing your fingers is not enough *

Yi Herng Ong
John Morrow
Yu Qiu
Kartik Gupta
Ravi Balasubramanian
Cindy M. Grimm

Grasping a simple object from the side is easy — unless the object is almost as big as the hand or space constraints require positioning the robot hand awkwardly with respect to the object. We show that humans — when faced with this challenge — adopt coordinated finger movements which enable them to successfully grasp objects even from these awkward poses. We also show that it is relatively straight forward to implement these strategies autonomously. Our human-studies approach asks participants to perform grasping task by either “puppetteering” a robotic manipulator that is identical (geometrically and kinematically) to a popular underactuated robotic manipulator (the Barrett hand), or using sliders to control the original Barrett hand. Unlike previous studies, this enables us to directly capture and compare human manipulation strategies with robotic ones. Our observation is that, while humans employ underactuation, how they use it is fundamentally different (and more effective) than that found in existing hardware.

Details

ICML Conference 2017 Conference Paper

Nearly Optimal Robust Matrix Completion

Yeshwanth Cherapanamjeri
Kartik Gupta
Prateek Jain 0002

In this paper, we consider the problem of Robust Matrix Completion (RMC) where the goal is to recover a low-rank matrix by observing a small number of its entries out of which a few can be arbitrarily corrupted. We propose a simple projected gradient descent-based method to estimate the low-rank matrix that alternately performs a projected gradient descent step and cleans up a few of the corrupted entries using hard-thresholding. Our algorithm solves RMC using nearly optimal number of observations while tolerating a nearly optimal number of corruptions. Our result also implies significant improvement over the existing time complexity bounds for the low-rank matrix completion problem. Finally, an application of our result to the robust PCA problem (low-rank+sparse matrix separation) leads to nearly linear time (in matrix dimensions) algorithm for the same; existing state-of-the-art methods require quadratic time. Our empirical results corroborate our theoretical results and show that even for moderate sized problems, our method for robust PCA is an order of magnitude faster than the existing methods.

Details