Search Results for author:
Found 40 papers, 12 papers with code
Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
We introduce a method to train Binarized Neural Networks (BNNs) - neural networks with binary weights and activations at run-time.
Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits.
Learn on Source, Refine on Target:A Model Transfer Learning Framework with Random Forests
We propose novel model transfer-learning methods that refine a decision forest model M learned within a "source" domain using a training set sampled from a "target" domain, assumed to be a variation of the source.
Deep Anomaly Detection Using Geometric Transformations
We consider the problem of anomaly detection in images, and present a new detection technique.
Ranked #12 on
Anomaly Detection
on One-class CIFAR-100
SelectiveNet: A Deep Neural Network with an Integrated Reject Option
We consider the problem of selective prediction (also known as reject option) in deep neural networks, and introduce SelectiveNet, a deep neural architecture with an integrated reject option.
Multi-Hop Paragraph Retrieval for Open-Domain Question Answering
This paper is concerned with the task of multi-hop open-domain Question Answering (QA).
Ranked #55 on
Question Answering
on HotpotQA
A framework for benchmarking class-out-of-distribution detection and its application to ImageNet
In this paper we present a novel framework to benchmark the ability of image classifiers to detect class-out-of-distribution instances (i. e., instances whose true labels do not appear in the training distribution) at various levels of detection difficulty.
TransBoost: Improving the Best ImageNet Performance using Deep Transduction
This paper deals with deep transductive learning, and proposes TransBoost as a procedure for fine-tuning any deep neural model to improve its performance on any (unlabeled) test set provided at training time.
Ranked #1 on
Image Classification
on SUN397
Deep Active Learning with a Neural Architecture Search
We consider active learning of deep neural networks.
What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers
Here we examine the relationship between deep architectures and their respective training regimes, with their corresponding selective prediction and uncertainty estimation performance.
Disrupting Deep Uncertainty Estimation Without Harming Accuracy
In this paper we present a novel and simple attack, which unlike adversarial attacks, does not cause incorrect predictions but instead cripples the network's capacity for uncertainty estimation.
Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers
We consider the problem of uncertainty estimation in the context of (non-Bayesian) deep neural classification.
Deep Active Learning over the Long Tail
This paper is concerned with pool-based active learning for deep neural networks.
Selective Classification for Deep Neural Networks
Our method allows a user to set a desired risk level.
Growth-Optimal Portfolio Selection under CVaR Constraints
Online portfolio selection research has so far focused mainly on minimizing regret defined in terms of wealth growth.
The Prediction Advantage: A Universally Meaningful Performance Measure for Classification and Regression
We introduce the Prediction Advantage (PA), a novel performance measure for prediction functions under any loss function (e. g., classification or regression).
The Relationship Between Agnostic Selective Classification Active Learning and the Disagreement Coefficient
We focus on the agnostic setting, for which there is a known algorithm called LESS that learns a PCS classifier and achieves a fast rejection rate (depending on Hanneke's disagreement coefficient) under strong assumptions.
Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision
We propose a scheme for training a computerized agent to perform complex human tasks such as highway steering.
Multi-Objective Non-parametric Sequential Prediction
Recently, an algorithm for dealing with several objective functions in the i. i. d.
Online Learning of Commission Avoidant Portfolio Ensembles
We present a novel online ensemble learning strategy for portfolio selection.
Online Learning of Portfolio Ensembles with Sector Exposure Regularization
We consider online learning of ensembles of portfolio selection algorithms and aim to regularize risk by encouraging diversification with respect to a predefined risk-driven grouping of stocks.
A Compression Technique for Analyzing Disagreement-Based Active Learning
We introduce a new and improved characterization of the label complexity of disagreement-based active learning, in which the leading quantity is the version space compression set size.
Transductive Rademacher Complexity and its Applications
We develop a technique for deriving data-dependent error bounds for transductive learning algorithms based on transductive Rademacher complexity.
Semantic Sort: A Supervised Approach to Personalized Semantic Relatedness
We propose and study a novel supervised approach to learning statistical semantic relatedness models from subjectively annotated training examples.
Pointwise Tracking the Optimal Regression Function
This paper examines the possibility of a `reject option' in the context of least squares regression.
Selective Prediction of Financial Trends with Hidden Markov Models
Our results indicate that both methods are effective, and that the sHMM model is superior.
Agnostic Selective Classification
For a learning problem whose associated excess loss class is $(\beta, B)$-Bernstein, we show that it is theoretically possible to track the same classification performance of the best (unknown) hypothesis in our class, provided that we are free to abstain from prediction in some region of our choice.
ML for Flood Forecasting at Scale
We propose to build on these strengths and develop ML systems for timely and accurate riverine flood prediction.
Leveraging Auxiliary Text for Deep Recognition of Unseen Visual Relationships
Our model relies on a shared text--image representation of subject-verb-object relationships appearing in the text, and object interactions in images.
MadNet: Using a MAD Optimization for Defending Against Adversarial Attacks
Given a deep neural network (DNN) for a classification problem, an application of MAD optimization results in MadNet, a version of the original network, now equipped with an adversarial defense mechanism.
Accurate Hydrologic Modeling Using Less Information
Joint models are a common and important tool in the intersection of machine learning and the physical sciences, particularly in contexts where real-world measurements are scarce.
DNF-Net: A Neural Architecture for Tabular Data
A challenging open question in deep learning is how to handle tabular data.
HydroNets: Leveraging River Structure for Hydrologic Modeling
In this work we present a novel family of hydrologic models, called HydroNets, which leverages river network structure.
Net-DNF: Effective Deep Modeling of Tabular Data
A challenging open question in deep learning is how to handle tabular data.
Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN
Our ScalableAlphaZero is capable of learning to play incrementally on small boards, and advancing to play on large ones.
How to measure deep uncertainty estimation performance and which models are naturally better at providing it
Moreover, we consider some of the most popular estimation performance metrics previously proposed including AUROC, ECE, AURC, and coverage for selective accuracy constraint.
Improved Detection of Adversarial Attacks via Penetration Distortion Maximization
This paper is concerned with the defense of deep models against adversarial at- tacks.
Using Fictitious Class Representations to Boost Discriminative Zero-Shot Learners
Focusing on discriminative zero-shot learning, in this work we introduce a novel mechanism that dynamically augments during training the set of seen classes to produce additional fictitious classes.
Which models are innately best at uncertainty estimation?
Due to the comprehensive nature of this paper, it has been updated and split into two separate papers: "A Framework For Benchmarking Class-out-of-distribution Detection And Its Application To ImageNet" and "What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers".
