715 citations · 1.4k across the 35 of their papers we have counts for
37 papers
Adjacent Leader Decentralized Stochastic Gradient Descent
Haoze He, Jing Wang, Anna Choromanska
This work focuses on the decentralized deep learning optimization framework. We propose Adjacent Leader Decentralized Gradient Descent (AL-DSGD), for improving final model performa…
GRAWA: Gradient-based Weighted Averaging for Distributed Training of Deep Learning Models
Tolga Dimlioglu, Anna Choromanska
We study distributed training of deep learning models in time-constrained environments. We propose a new algorithm that periodically pulls workers towards the center variable compu…
TAME: Task Agnostic Continual Learning using Multiple Experts
Haoran Zhu, Maryam Majzoubi, Arihant Jain +1
The goal of lifelong learning is to continuously learn from non-stationary distributions, where the non-stationarity is typically imposed by a sequence of distinct tasks. Prior wor…
ERASE-Net: Efficient Segmentation Networks for Automotive Radar Signals
Shihong Fang, Haoran Zhu, Devansh Bisla +4
Among various sensors for assisted and autonomous driving systems, automotive radar has been considered as a robust and low-cost solution even in adverse weather or lighting condit…
Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape
Devansh Bisla, Jing Wang, Anna Choromanska
In this paper, we study the sharpness of a deep learning (DL) loss landscape around local minima in order to reveal systematic mechanisms underlying the generalization abilities of…
AutoDrop: Training Deep Learning Models with Automatic Learning Rate Drop
Yunfei Teng, Jing Wang, Anna Choromanska
Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a defined learning rate schedule, i.e., the learning ra…
ESAFE: Enterprise Security and Forensics at Scale
Bernard McShea, Kevin Wright, Denley Lam +7
Securing enterprise networks presents challenges in terms of both their size and distributed structure. Data required to detect and characterize malicious activities may be diffuse…
A Theoretical-Empirical Approach to Estimating Sample Complexity of DNNs
Devansh Bisla, Apoorva Nandini Saridena, Anna Choromanska
This paper focuses on understanding how the generalization error scales with the amount of the training data for deep neural networks (DNNs). Existing techniques in statistical lea…
Approximating Ground State Energies and Wave Functions of Physical Systems with Neural Networks
Cesar Lema, Anna Choromanska
Quantum theory has been remarkably successful in providing an understanding of physical systems at foundational scales. Solving the Schrödinger equation provides full knowledge of…
SGB: Stochastic Gradient Bound Method for Optimizing Partition Functions
Jing Wang, Anna Choromanska
This paper addresses the problem of optimizing partition functions in a stochastic learning setting. We propose a stochastic variant of the bound majorization algorithm that relies…
Overcoming Catastrophic Forgetting via Direction-Constrained Optimization
Yunfei Teng, Anna Choromanska, Murray Campbell +3
This paper studies a new design of the optimization algorithm for training deep learning models with a fixed architecture of the classification network in a continual learning fram…
Backdoor Attacks on the DNN Interpretation System
Shihong Fang, Anna Choromanska
Interpretability is crucial to understand the inner workings of deep neural networks (DNNs) and many interpretation methods generate saliency maps that highlight parts of the input…
Multi-modal Experts Network for Autonomous Driving
Shihong Fang, Anna Choromanska
End-to-end learning from sensory data has shown promising results in autonomous driving. While employing many sensors enhances world perception and should lead to more robust and r…
Learning to Score Behaviors for Guided Policy Optimization
Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang +3
We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing t…
LdSM: Logarithm-depth Streaming Multi-label Decision Trees
Maryam Majzoubi, Anna Choromanska
We consider multi-label classification where the goal is to annotate each data point with the most relevant of labels from an extremely large label set. Efficient…
Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models: Extension
Yunfei Teng, Wenbo Gao, Francois Chalus +3
We consider distributed optimization under communication constraints for training deep learning models. We propose a new algorithm, whose parameter updates rely on two forces: a re…
Towards Automated Melanoma Detection with Deep Learning: Data Purification and Augmentation
Devansh Bisla, Anna Choromanska, Jennifer A. Stein +2
Melanoma is one of the ten most common cancers in the US. Early detection is crucial for survival, but often the cancer is diagnosed in the fatal stage. Deep learning has the poten…
Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy
Naman Patel, Apoorva Nandini Saridena, Anna Choromanska +2
The paper proposes an on-line monitoring framework for continuous real-time safety/security in learning-based control systems (specifically application to a unmanned ground vehicle…
Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Anna Choromanska, Benjamin Cowen, Sadhana Kumaravel +8
Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art metho…
VisualBackProp for learning using privileged information with CNNs
Devansh Bisla, Anna Choromanska
In many machine learning applications, from medical diagnostics to autonomous driving, the availability of prior knowledge can be used to improve the predictive performance of lear…
Invertible Autoencoder for domain adaptation
Yunfei Teng, Anna Choromanska, Mariusz Bojarski
The unsupervised image-to-image translation aims at finding a mapping between the source () and target () image domains, where in many applications aligned image pairs are no…
LSALSA: Accelerated Source Separation via Learned Sparse Coding
Benjamin Cowen, Apoorva Nandini Saridena, Anna Choromanska
We propose an efficient algorithm for the generalized sparse coding (SC) inference problem. The proposed framework applies to both the single dictionary setting, where each data po…
A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI
Shervin Minaee, Yao Wang, Anna Choromanska +6
Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and sym…
Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
Mariusz Bojarski, Philip Yeres, Anna Choromanska +4
As part of a complete software stack for autonomous driving, NVIDIA has created a neural-network-based system, known as PilotNet, which outputs steering angles given images of the…