Search Results for author:
Found 99 papers, 22 papers with code
Minimax Rate for Learning From Pairwise Comparisons in the BTL Model
We consider the problem of learning the qualities w_1, ... , w_n of a collection of items by performing noisy comparisons among them.
Deep Companion Learning: Enhancing Generalization Through Historical Consistency
We propose Deep Companion Learning (DCL), a novel training method for Deep Neural Networks (DNNs) that enhances generalization by penalizing inconsistent model predictions compared to its historical performance.
Testing the Feasibility of Linear Programs with Bandit Feedback
While the recent literature has seen a surge in the study of constrained bandit problems, all existing methods for these begin by assuming the feasibility of the underlying problem.
SynCDR : Training Cross Domain Retrieval Models with Synthetic Data
In cross-domain retrieval, a model is required to identify images from the same semantic category across two visual domains.
Learning Human Action Recognition Representations Without Real Humans
To this end, we present, for the first time, a benchmark that leverages real-world videos with humans removed and synthetic data containing virtual humans to pre-train a model.
Learning to Drive Anywhere
Human drivers can seamlessly adapt their driving decisions across geographical locations with diverse conditions and rules of the road, e. g., left vs. right-hand traffic.
Efficient Edge Inference by Selective Query
Training a hybrid learner is difficult since we lack annotations of hard edge-examples.
Scaffolding a Student to Instill Knowledge
We propose a novel knowledge distillation (KD) method to selectively instill teacher knowledge into a student model motivated by situations where the student's capacity is significantly smaller than that of the teachers.
Filtering Context Mitigates Scarcity and Selection Bias in Political Ideology Prediction
We propose a novel supervised learning approach for political ideology prediction (PIP) that is capable of predicting out-of-distribution inputs.
Safe Linear Bandits over Unknown Polytopes
We then analyse a natural doubly-optimistic strategy for the safe linear bandit problem, DOSS, which uses optimistic estimates of both reward and safety risks to select actions, and show that despite the lack of knowledge of constraints or feasible points, DOSS simultaneously obtains tight instance-dependent $O(\log^2 T)$ bounds on efficacy regret, and $\tilde O(\sqrt{T})$ bounds on safety violations.
Fine-grained Few-shot Recognition by Deep Object Parsing
An object is parsed by estimating the locations of these K parts and a set of active templates that can reconstruct the part features.
FedHeN: Federated Learning in Heterogeneous Networks
We propose a novel training recipe for federated learning with heterogeneous networks where each device can have different architectures.
Learning Compositional Representations for Effective Low-Shot Generalization
RPC encodes images by first decomposing them into salient parts, and then encoding each part as a mixture of a small number of prototypes, each representing a certain concept.
Strategies for Safe Multi-Armed Bandits with Logarithmic Regret and Risk
We investigate a natural but surprisingly unstudied approach to the multi-armed bandit problem under safety risk constraints.
Task2Sim: Towards Effective Pre-Training and Transfer From Synthetic Data
It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance.
Condensing CNNs With Partial Differential Equations
Convolutional neural networks (CNNs) rely on the depth of the architecture to obtain complex features.
Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data
It is thus better to tailor synthetic pre-training data to a specific downstream task, for best performance.
Federated Learning Based on Dynamic Regularization
We propose a novel federated learning method for distributively training neural network models, where the server orchestrates cooperation between a subset of randomly chosen devices in each round.
Faster Algorithms for Learning Convex Functions
For the task of convex Lipschitz regression, we establish that our proposed algorithm converges with iteration complexity of $ O(n\sqrt{d}/\epsilon)$ for a dataset $\bm X \in \mathbb R^{n\times d}$ and $\epsilon > 0$.
Online Selective Classification with Limited Feedback
For example, this may model an adaptive decision to invoke more resources on this instance.
Hybrid Cloud-Edge Networks for Efficient Inference
The first network is a low-capacity network that can be deployed on an edge device, whereas the second is a high-capacity network deployed in the cloud.
Bandit Quickest Changepoint Detection
Many industrial and security applications employ a suite of sensors for detecting abrupt changes in temporal behavior patterns.
Training Recurrent Neural Networks via Forward Propagation Through Time
BPTT updates RNN parameters on an instance by back-propagating the error in time over the entire sequence length, and as a result, leads to poor trainability due to the well-known gradient explosion/decay phenomena.
Time Adaptive Recurrent Neural Network
We propose a learning method that, dynamically modifies the time-constants of the continuous-time counterpart of a vanilla RNN.
Effectively Leveraging Attributes for Visual Similarity
This enables our model to identify that two images contain the same attribute, but can have it deemed irrelevant (e. g., due to fine-grained differences between them) and ignored for measuring similarity between the two images.
Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency
With our Pretraining and Consistency (PAC) approach, we achieve state of the art target accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Limits on Testing Structural Changes in Ising Models
We present novel information-theoretic limits on detecting sparse changes in Isingmodels, a problem that arises in many applications where network changes canoccur due to some external stimuli.
Online Algorithm for Unsupervised Sequential Selection with Contextual Information
In this paper, we study Contextual Unsupervised Sequential Selection (USS), a new variant of the stochastic contextual bandits problem where the loss of an arm cannot be inferred from the observed feedback.
Selective Classification via One-Sided Prediction
We propose a novel method for selective classification (SC), a problem which allows a classifier to abstain from predicting some instances, thus trading off accuracy against coverage (the fraction of instances predicted).
RNN Training along Locally Optimal Trajectories via Frank-Wolfe Algorithm
We propose to utilize the Frank-Wolfe (FW) algorithm in this context.
Piecewise Linear Regression via a Difference of Convex Functions
We present a new piecewise linear regression methodology that utilizes fitting a difference of convex functions (DC functions) to the data.
RNNs Incrementally Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate.
Budget Learning via Bracketing
We propose a new formulation for the BL problem via the concept of bracketings.
Efficient Near-Optimal Testing of Community Changes in Balanced Stochastic Block Models
Overall, for large changes, $s \gg \sqrt{n}$, we need only $\mathrm{SNR}= O(1)$ whereas a na\"ive test based on community recovery with $O(s)$ errors requires $\mathrm{SNR}= \Theta(\log n)$.
Shallow RNN: Accurate Time-series Classification on Resource Constrained Devices
The second layer consumes the output of the first layer using a second RNN thus capturing long dependencies.
Dont Even Look Once: Synthesizing Features for Zero-Shot Detection
Zero-shot detection, namely, localizing both seen and unseen objects, increasingly gains importance for large-scale applications, with large number of object classes, since, collecting sufficient annotated data with ground truth bounding boxes is simply not scalable.
RNNs Evolving on an Equilibrium Manifold: A Panacea for Vanishing and Exploding Gradients?
Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate.
Learning to Approximate a Bregman Divergence
Bregman divergences generalize measures such as the squared Euclidean distance and the KL divergence, and arise throughout many areas of machine learning.
Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers
We consider worker skill estimation for the single-coin Dawid-Skene crowdsourcing model.
Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability
We show that such self-feedback helps stabilize the hidden state transitions leading to fast convergence during training while efficiently learning discriminative latent features that result in state-of-the-art results on several benchmark datasets at test-time.
Graph Resistance and Learning from Pairwise Comparisons
The algorithm has a relative error decay that scales with the square root of the graph resistance, and provide a matching lower bound (up to log factors).
Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training "models from scratch," and methods that adapt existing models, trained on the presented training environment, to the new scenario are required.
Online Algorithm for Unsupervised Sensor Selection
We set up the USS problem as a stochastic partial monitoring problem and develop an algorithm with sub-linear regret under the WD property.
Testing Changes in Communities for the Stochastic Block Model
Overall, for large changes, $s \gg \sqrt{n}$, we need only $\mathrm{SNR}= O(1)$ whereas a na\"ive test based on community recovery with $O(s)$ errors requires $\mathrm{SNR}= \Theta(\log n)$.
Generalized Zero-Shot Recognition based on Visually Semantic Embedding
To bridge the gap, we propose a novel low-dimensional embedding of visual instances that is "visually semantic."
Cost-Aware Fine-Grained Recognition for IoTs Based on Sequential Fixations
We consider the problem of fine-grained classification on an edge camera device that has limited power.
Robust Text Classifier on Test-Time Budgets
We propose a generic and interpretable learning framework for building robust text classification model that achieves accuracy comparable to full models under test-time budget constraints.
Lower Bounds for Two-Sample Structural Change Detection in Ising and Gaussian Models
We study the trade-off between the sample sizes and the reliability of change detection, measured as a minimax risk, for the important cases of the Ising models and the Gaussian Markov random fields restricted to the models which have network structures with $p$ nodes and degree at most $d$, and obtain information-theoretic lower bounds for reliable change detection over these models.
Connected Subgraph Detection with Mirror Descent on SDPs
We propose a novel, computationally efficient mirror-descent based optimization framework for subgraph detection in graph-structured data.
Crowdsourcing with Sparsely Interacting Workers
We then formulate a weighted rank-one optimization problem to estimate skills based on observations on an irreducible, aperiodic interaction graph.
Sequential Dynamic Decision Making with Deep Neural Nets on a Test-Time Budget
Deep neural network (DNN) based approaches hold significant potential for reinforcement learning (RL) and have already shown remarkable gains over state-of-art methods in a number of applications.
Adaptive Classification for Prediction Under a Budget
Our novel bottom-up method first trains a high-accuracy complex model.
Comments on the proof of adaptive submodular function minimization
We point out an issue with Theorem 5 appearing in "Group-based active query selection for rapid diagnosis in time-critical situations".
Dynamic Model Selection for Prediction Under a Budget
Our objective is to minimize overall average cost without sacrificing accuracy.
Field of Groves: An Energy-Efficient Random Forest
In this work, we present a field of groves (FoG) implementation of random forests (RF) that achieves an accuracy comparable to CNNs and SVMs under tight energy budgets.
Adaptive Neural Networks for Efficient Inference
We first pose an adaptive network evaluation scheme, where we learn a system to adaptively choose the components of a deep network to be evaluated for each example.
Learning Joint Feature Adaptation for Zero-Shot Recognition
In this paper we propose a novel framework of learning data-dependent feature transforms for scoring similarity between an arbitrary pair of source and target data instances to account for the wide variability in target domain.
Sequential Learning without Feedback
We reduce USS to a special case of multi-armed bandit problem with side information and develop polynomial time algorithms that achieve sublinear regret.
Clustering and Community Detection with Imbalanced Clusters
Spectral clustering methods which are frequently used in clustering and community detection applications are sensitive to the specific graph constructions particularly when imbalanced clusters are present.
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
Geometrically, gender bias is first shown to be captured by a direction in the word embedding.
Quantifying and Reducing Stereotypes in Word Embeddings
Machine learning algorithms are optimized to model statistical properties of the training data.
Pruning Random Forests for Prediction on a Budget
We propose to prune a random forest (RF) for resource-constrained prediction.
Resource Constrained Structured Prediction
We study the problem of structured prediction under test-time budget constraints.
Learning Minimum Volume Sets and Anomaly Detectors from KNN Graphs
We propose a non-parametric anomaly detection algorithm for high dimensional data.
Optimally Pruning Decision Tree Ensembles With Feature Cost
We propose a novel 0-1 integer program formulation for ensemble pruning.
Zero-Shot Learning via Joint Latent Similarity Embedding
It takes an arbitrary pair of source and target domain instances as input and predicts whether or not they come from the same class, i. e. whether there is a match.
Efficient Training of Very Deep Neural Networks for Supervised Hashing
In this paper, we propose training very deep neural networks (DNNs) for supervised learning of hash codes.
Sequential Optimization for Efficient High-Quality Object Proposal Generation
We propose a novel object proposal algorithm, BING++, which inherits the virtue of good computational efficiency of BING but significantly improves its proposal localization quality.
Efficient Learning by Directed Acyclic Graph For Resource Constrained Prediction
We learn node policies in the DAG by reducing the global objective to a series of cost sensitive learning problems.
Algorithms for Linear Bandits on Polyhedral Sets
We then provide a nearly optimal algorithm and show that its expected regret scales as $O(N\log^{1+\epsilon}(T))$ for an arbitrary small $\epsilon >0$.
Group Membership Prediction
In this context we propose a novel probability model and introduce latent {\em view-specific} and {\em view-shared} random variables to jointly account for the view-specific appearance and cross-view similarities among data instances.
Zero-Shot Learning via Semantic Similarity Embedding
In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided.
Sensor Selection by Linear Programming
We decompose the problem, which is known to be intractable, into combinatorial (tree structures) and continuous parts (node decision rules) and propose to solve them separately.
Necessary and Sufficient Conditions and a Provably Efficient Algorithm for Separable Topic Discovery
We develop necessary and sufficient conditions and a novel provably consistent and efficient algorithm for discovering topics (latent factors) from observations (documents) that are realized from a probabilistic mixture of shared latent factors that have certain properties.
Cheap Bandits
We consider stochastic sequential learning problems where the learner can observe the \textit{average reward of several actions}.
Learning Mixed Membership Mallows Models from Pairwise Comparisons
Our key algorithmic insight for estimation is to establish a statistical connection between M4 and topic models by viewing pairwise comparisons as words, and users as documents.
Feature-Budgeted Random Forest
We seek decision rules for prediction-time cost reduction, where complete data is available for training, but during prediction-time, each feature can only be acquired for an additional cost.
Learning Efficient Anomaly Detectors from $K$-NN Graphs
We propose a non-parametric anomaly detection algorithm for high dimensional data.
Minimax Optimal Sparse Signal Recovery with Poisson Statistics
We are motivated by problems that arise in a number of applications such as Online Marketing and Explosives detection, where the observations are usually modeled using Poisson statistics.
Max-Cost Discrete Function Evaluation Problem under a Budget
We develop a broad class of \emph{admissible} impurity functions that admit monomials, classes of polynomials, and hinge-loss functions that allow for flexible impurity design with provably optimal approximation bounds.
A Topic Modeling Approach to Ranking
We propose a topic modeling approach to the prediction of preferences in pairwise comparisons.
Efficient Minimax Signal Detection on Graphs
Several problems such as network intrusion, community detection, and disease outbreak can be described by observations attributed to nodes or edges of a graph.
A Novel Visual Word Co-occurrence Model for Person Re-identification
We first map each pixel of an image to a visual word using a codebook, which is learned in an unsupervised manner.
RAPID: Rapidly Accelerated Proximal Gradient Algorithms for Convex Minimization
In this paper, we propose a new algorithm to speed-up the convergence of accelerated proximal gradient (APG) methods.
PRISM: Person Re-Identification via Structured Matching
From a visual perspective re-id is challenging due to significant changes in visual appearance of individuals in cameras with different pose, illumination and calibration.
A Rank-SVM Approach to Anomaly Detection
The resulting anomaly detector is shown to be asymptotically optimal and adaptive in that for any false alarm rate alpha, its decision region converges to the alpha-percentile level set of the unknown underlying density.
Retrieval in Long Surveillance Videos using User Described Motion and Object Attributes
We present a content-based retrieval method for long surveillance videos both for wide-area (Airborne) as well as near-field imagery (CCTV).
Sparse Recovery with Linear and Nonlinear Observations: Dependent and Noisy Data
We formulate sparse support recovery as a salient set identification problem and use information-theoretic analyses to characterize the recovery performance and sample complexity.
Information-Theoretic Bounds for Adaptive Sparse Recovery
We show that adaptivity cannot decrease sample complexity in group testing, 1-bit CS and CS with linear sparsity.
Sensing-Aware Kernel SVM
We propose a novel approach for designing kernels for support vector machines (SVMs) when the class label is linked to the observation through a latent state and the likelihood function of the observation given the state (the sensing model) is available.
Necessary and Sufficient Conditions for Novel Word Detection in Separable Topic Models
The simplicial condition and other stronger conditions that imply it have recently played a central role in developing polynomial time algorithms with provable asymptotic consistency and sample complexity guarantees for topic estimation in separable topic models.
Spectral Clustering with Imbalanced Data
Spectral clustering is sensitive to how graphs are constructed from data particularly when proximal and imbalanced clusters are present.
Sparse Signal Processing with Linear and Nonlinear Observations: A Unified Shannon-Theoretic Approach
These mutual information expressions unify conditions for both linear and nonlinear observations.
An Impossibility Result for High Dimensional Supervised Learning
We study high-dimensional asymptotic performance limits of binary supervised classification problems where the class conditional densities are Gaussian with unknown means and covariances and the number of signal dimensions scales faster than the number of labeled training samples.
Local Supervised Learning through Space Partitioning
We show that space partitioning can be equivalently reformulated as a supervised learning problem and consequently any discriminative learning method can be utilized in conjunction with our approach.
Probabilistic Belief Revision with Structural Constraints
Experts (human or computer) are often required to assess the probability of uncertain events.
Anomaly Detection with Score functions based on Nearest Neighbor Graphs
We propose a novel non-parametric adaptive anomaly detection algorithm for high dimensional data based on score functions derived from nearest neighbor graphs on n-point nominal data.
