Anna Choromanska

research

∙ 01/20/2022

Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

In this paper, we study the sharpness of a deep learning (DL) loss lands...

Devansh Bisla, et al. ∙

research

∙ 12/08/2021

ESAFE: Enterprise Security and Forensics at Scale

Securing enterprise networks presents challenges in terms of both their ...

Bernard McShea, et al. ∙

research

∙ 11/30/2021

AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop

Modern deep learning (DL) architectures are trained using variants of th...

Yunfei Teng, et al. ∙

research

∙ 05/05/2021

A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs

This paper focuses on understanding how the generalization error scales ...

Devansh Bisla, et al. ∙

research

∙ 11/25/2020

Continual learning with direction-constrained optimization

This paper studies a new design of the optimization algorithm for traini...

Yunfei Teng, et al. ∙

research

∙ 11/21/2020

Backdoor Attacks on the DNN Interpretation System

Interpretability is crucial to understand the inner workings of deep neu...

Shihong Fang, et al. ∙

research

∙ 11/03/2020

SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions

This paper addresses the problem of optimizing partition functions in a ...

Jing Wang, et al. ∙

research

∙ 09/18/2020

Multi-modal Experts Network for Autonomous Driving

End-to-end learning from sensory data has shown promising results in aut...

Shihong Fang, et al. ∙

research

∙ 06/11/2019

Wasserstein Reinforcement Learning

We propose behavior-driven optimization via Wasserstein distances (WDs) ...

Aldo Pacchiano, et al. ∙

research

∙ 05/24/2019

LdSM: Logarithm-depth Streaming Multi-label Decision Trees

We consider multi-label classification where the goal is to annotate eac...

Maryam Majzoubi, et al. ∙

research

∙ 05/24/2019

Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models

We consider distributed optimization under communication constraints for...

Yunfei Teng, et al. ∙

research

∙ 02/16/2019

Skin Lesion Segmentation and Classification with Deep Learning System

Melanoma is one of the ten most common cancers in the US. Early detectio...

Devansh Bisla, et al. ∙

research

∙ 11/12/2018

Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy

The paper proposes an on-line monitoring framework for continuous real-t...

Naman Patel, et al. ∙

research

∙ 06/24/2018

Beyond Backprop: Alternating Minimization with co-Activation Memory

We propose a novel online algorithm for training deep feedforward neural...

Anna Choromanska, et al. ∙

research

∙ 05/24/2018

VisualBackProp for learning using privileged information with CNNs

In many machine learning applications, from medical diagnostics to auton...

Devansh Bisla, et al. ∙

research

∙ 02/13/2018

LSALSA: efficient sparse coding in single and multiple dictionary settings

We propose an efficient sparse coding (SC) framework for obtaining spars...

Benjamin Cowen, et al. ∙

research

∙ 02/10/2018

Invertible Autoencoder for domain adaptation

The unsupervised image-to-image translation aims at finding a mapping be...

Yunfei Teng, et al. ∙

research

∙ 02/08/2018

A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI

Mild traumatic brain injury (mTBI) is a growing public health problem wi...

Shervin Minaee, et al. ∙

research

∙ 04/25/2017

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

As part of a complete software stack for autonomous driving, NVIDIA has ...

Mariusz Bojarski, et al. ∙

research

∙ 11/16/2016

VisualBackProp: efficient visualization of CNNs

This paper proposes a new method, that we call VisualBackProp, for visua...

Mariusz Bojarski, et al. ∙

research

∙ 11/06/2016

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

This paper proposes a new optimization algorithm called Entropy-SGD for ...

Pratik Chaudhari, et al. ∙

research

∙ 10/14/2016

Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation

We consider multi-class classification where the predictor has a hierarc...

Yacine Jernite, et al. ∙

research

∙ 11/16/2015

Binary embeddings with structured hashed projections

We consider the hashing mechanism for constructing binary embeddings, th...

Anna Choromanska, et al. ∙

research

∙ 12/20/2014

Deep learning with Elastic Averaging SGD

We study the problem of stochastic optimization for deep learning in the...

Sixin Zhang, et al. ∙

research

∙ 11/30/2014

The Loss Surfaces of Multilayer Networks

We study the connection between the highly non-convex loss function of a...

Anna Choromanska, et al. ∙

research

∙ 10/26/2014

Differentially- and non-differentially-private random decision trees

We consider supervised learning with random decision trees, where the tr...

Mariusz Bojarski, et al. ∙

research

∙ 09/05/2013

Semistochastic Quadratic Bound Methods

Partition functions arise in a variety of settings, including conditiona...

Aleksandr Y. Aravkin, et al. ∙

Anna Choromanska

Featured Co-authors

Stefano Soatto

Yann LeCun

Jing Wang

Yao Wang

Adrian Weller

David Sontag

Sanjiv Kumar

Krzysztof Choromanski

Shervin Minaee

Aldo Pacchiano

Brian Kingsbury

Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape

ESAFE: Enterprise Security and Forensics at Scale

AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop

A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs

Continual learning with direction-constrained optimization

Backdoor Attacks on the DNN Interpretation System

SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions

Multi-modal Experts Network for Autonomous Driving

Wasserstein Reinforcement Learning

LdSM: Logarithm-depth Streaming Multi-label Decision Trees

Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models

Skin Lesion Segmentation and Classification with Deep Learning System

Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy

Beyond Backprop: Alternating Minimization with co-Activation Memory

VisualBackProp for learning using privileged information with CNNs

LSALSA: efficient sparse coding in single and multiple dictionary settings

Invertible Autoencoder for domain adaptation

A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

VisualBackProp: efficient visualization of CNNs

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation

Binary embeddings with structured hashed projections

Deep learning with Elastic Averaging SGD

The Loss Surfaces of Multilayer Networks

Differentially- and non-differentially-private random decision trees

Semistochastic Quadratic Bound Methods