Search Results for author:
Found 25 papers, 5 papers with code
Simple Weak Coresets for Non-Decomposable Classification Measures
While coresets have been growing in terms of their application, barring few exceptions, they have mostly been limited to unsupervised settings.
A Novel Pipeline for Improving Optical Character Recognition through Post-processing Using Natural Language Processing
Optical Character Recognition (OCR) technology finds applications in digitizing books and unstructured documents, along with applications in other domains such as mobility statistics, law enforcement, traffic, security systems, etc.
Optical Character Recognition
Optical Character Recognition (OCR)
Improving Expressivity of Graph Neural Networks using Localization
We focus on the specific problem of subgraph counting and give localized versions of $k-$WL for any $k$.
Ranked #1 on
Subgraph Counting - Chordal C4
on Synthetic Graph
OSSuM: A Gradient-Free Approach For Pruning Neural Networks At Initialization
Recent works attempt to prune neural networks at initialization to design sparse networks that can be trained efficiently.
Statistical Measures For Defining Curriculum Scoring Function
Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance.
A Simple Approach To Define Curricula For Training Neural Networks
Curriculum learning is a training strategy that sorts the training examples by their difficulty and gradually exposes them to the learner.
Online Coresets for Clustering with Bregman Divergences
Our first algorithm gives online coresets of size $\tilde{O}(\mbox{poly}(k, d,\epsilon,\mu))$ for $k$-clusterings according to any $\mu$-similar Bregman divergence.
On Additive Approximate Submodularity
We show that an approximately submodular function defined on a ground set of $n$ elements is $O(n^2)$ pointwise-close to a submodular function.
On Coresets For Regularized Regression
We propose a modified version of the lasso problem and obtain for it a coreset of size smaller than the least square regression.
Streaming Coresets for Symmetric Tensor Factorization
Factorizing tensors has recently become an important optimization module in a number of machine learning pipelines, especially in latent variable models.
Mallows Models for Top-k Lists
The classic Mallows model is a widely-used tool to realize distributions on per- mutations.
Discovering Topical Interactions in Text-based Cascades using Hidden Markov Hawkes Processes
We show using experiments on real and semi-synthetic data that HMHP is able to generalize better and recover the network strengths, topics and diffusion paths more accurately than state-of-the-art baselines.
Improved Linear Embeddings via Lagrange Duality
Near isometric orthogonal embeddings to lower dimensions are a fundamental tool in data science and machine learning.
SPECFACE - A Dataset of Human Faces Wearing Spectacles
This paper presents a database of human faces for persons wearing spectacles.
An Improved Algorithm for Eye Corner Detection
In this paper, a modified algorithm for the detection of nasal and temporal eye corners is presented.
Evaluation of Denoising Techniques for EOG signals based on SNR Estimation
This paper evaluates four algorithms for denoising raw Electrooculography (EOG) data based on the Signal to Noise Ratio (SNR).
Fast Computation of PERCLOS and Saccadic Ratio
This thesis describes the development of fast algorithms for the computation of PERcentage CLOSure of eyes (PERCLOS) and Saccadic Ratio (SR).
A Framework for Fast Face and Eye Detection
Face detection is an essential step in many computer vision applications like surveillance, tracking, medical analysis, facial expression analysis etc.
A Vision Based System for Monitoring the Loss of Attention in Automotive Drivers
In this paper, we propose a robust real time embedded platform to monitor the loss of attention of the driver during day as well as night driving conditions.
Crowdsourced judgement elicitation with endogenous proficiency
Our main contribution is a simple, new, mechanism for binary information elicitation for multiple tasks when agents have endogenous proficiencies, with the following properties: (i) Exerting maximum effort followed by truthful reporting of observations is a Nash equilibrium.
Selecting Diverse Features via Spectral Regularization
We compare our algorithms to traditional greedy and $\ell_1$-regularization schemes and show that we obtain a more diverse set of features that result in the regression problem being stable under perturbations.
Feature Hashing for Large Scale Multitask Learning
Empirical evidence suggests that hashing is an effective strategy for dimensionality reduction and practical nonparametric estimation.
Community Structure in Large Networks: Natural Cluster Sizes and the Absence of Large Well-Defined Clusters
A large body of work has been devoted to defining and identifying clusters or communities in social and information networks.
Data Structures and Algorithms Data Analysis, Statistics and Probability Physics and Society
