Search Results for author: Paul Bogdan

Found 27 papers, 10 papers with code

Exploring Neuron Interactions and Emergence in LLMs: From the Multifractal Analysis Perspective

1 code implementation14 Feb 2024 Xiongye Xiao, Chenyu Zhou, Heng Ping, Defu Cao, Yaxing Li, Yizhuo Zhou, Shixuan Li, Paul Bogdan

Prior studies on the emergence in large models have primarily focused on how the functional capabilities of large language models (LLMs) scale with model size.

Discovering Malicious Signatures in Software from Structural Interactions

no code implementations19 Dec 2023 Chenzhong Yin, Hantang Zhang, Mingxi Cheng, Xiongye Xiao, Xinghe Chen, Xin Ren, Paul Bogdan

Malware represents a significant security concern in today's digital landscape, as it can destroy or disable operating systems, steal sensitive user information, and occupy valuable disk space.

Malware Detection

Leveraging Reinforcement Learning and Large Language Models for Code Optimization

no code implementations9 Dec 2023 Shukai Duan, Nikos Kanakaris, Xiongye Xiao, Heng Ping, Chenyu Zhou, Nesreen K. Ahmed, Guixiang Ma, Mihai Capota, Theodore L. Willke, Shahin Nazarian, Paul Bogdan

We compare our framework with existing state-of-the-art models and show that it is more efficient with respect to speed and computational usage, as a result of the decrement in training steps and its applicability to models with fewer parameters.

Language Modelling reinforcement-learning +1

Leader-Follower Neural Networks with Local Error Signals Inspired by Complex Collectives

no code implementations11 Oct 2023 Chenzhong Yin, Mingxi Cheng, Xiongye Xiao, Xinghe Chen, Shahin Nazarian, Andrei Irimia, Paul Bogdan

Motivated by the intricacy of these collectives, we propose a neural network (NN) architecture inspired by the rules observed in nature's collective ensembles.

Neuro-Inspired Hierarchical Multimodal Learning

no code implementations27 Sep 2023 Xiongye Xiao, Gengshuo Liu, Gaurav Gupta, Defu Cao, Shixuan Li, Yaxing Li, Tianqing Fang, Mingxi Cheng, Paul Bogdan

Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world.

Fractional dynamics foster deep learning of COPD stage prediction

1 code implementation13 Mar 2023 Chenzhong Yin, Mihai Udrescu, Gaurav Gupta, Mingxi Cheng, Andrei Lihu, Lucretia Udrescu, Paul Bogdan, David M Mannino, Stefan Mihaicuta

The authors show that the fractional dynamic deep learning model (FDDLM) achieves a COPD prediction accuracy of 98. 66% and can serve as a robust alternative to spirometry.

Raising The Limit Of Image Rescaling Using Auxiliary Encoding

no code implementations12 Mar 2023 Chenzhong Yin, Zhihong Pan, Xin Zhou, Le Kang, Paul Bogdan

While the random sampling of latent variable $z$ is useful in generating diverse photo-realistic images, it is not desirable for image rescaling when accurate restoration of the HR image is more important.

Image Super-Resolution

Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations

1 code implementation4 Mar 2023 Xiongye Xiao, Defu Cao, Ruochen Yang, Gaurav Gupta, Gengshuo Liu, Chenzhong Yin, Radu Balan, Paul Bogdan

Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes.

Operator learning

End-to-end Mapping in Heterogeneous Systems Using Graph Representation Learning

no code implementations25 Apr 2022 Yao Xiao, Guixiang Ma, Nesreen K. Ahmed, Mihai Capota, Theodore Willke, Shahin Nazarian, Paul Bogdan

To enable heterogeneous computing systems with autonomous programming and optimization capabilities, we propose a unified, end-to-end, programmable graph representation learning (PGL) framework that is capable of mining the complexity of high-level programs down to the universal intermediate representation, extracting the specific computational patterns and predicting which code segments would run best on a specific core in heterogeneous hardware platforms.

Graph Representation Learning

Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System

no code implementations24 Apr 2022 Mohamed Ridha Znaidi, Gaurav Gupta, Paul Bogdan

Decentralized learning is an efficient emerging paradigm for boosting the computing capability of multiple bounded computing agents.

Federated Learning Privacy Preserving

Trust-aware Control for Intelligent Transportation Systems

no code implementations8 Nov 2021 Mingxi Cheng, Junyao Zhang, Shahin Nazarian, Jyotirmoy Deshmukh, Paul Bogdan

Many intelligent transportation systems are multi-agent systems, i. e., both the traffic participants and the subsystems within the transportation infrastructure can be modeled as interacting agents.

Management

Non-Linear Operator Approximations for Initial Value Problems

no code implementations ICLR 2022 Gaurav Gupta, Xiongye Xiao, Radu Balan, Paul Bogdan

The Padé exponential operator uses a $\textit{recurrent structure with shared parameters}$ to model the non-linearity compared to recent neural operators that rely on using multiple linear operator layers in succession.

The weighted mean trick – optimization strategies for robustness

no code implementations29 Sep 2021 Valeriu Balaban, Paul Bogdan

We prove that minimizing a weighted mean results in optimizing the higher-order moments of the loss distribution such as the variance, skewness, and kurtosis.

Pareto Policy Adaptation

no code implementations ICLR 2022 Panagiotis Kyriakis, Jyotirmoy Deshmukh, Paul Bogdan

We present a policy gradient method for Multi-Objective Reinforcement Learning under unknown, linear preferences.

Multi-Objective Reinforcement Learning reinforcement-learning

Multiwavelet-based Operator Learning for Differential Equations

1 code implementation NeurIPS 2021 Gaurav Gupta, Xiongye Xiao, Paul Bogdan

The solution of a partial differential equation can be obtained by computing the inverse operator map between the input and the solution space.

Operator learning

Non-Markovian Reinforcement Learning using Fractional Dynamics

no code implementations29 Jul 2021 Gaurav Gupta, Chenzhong Yin, Jyotirmoy V. Deshmukh, Paul Bogdan

Reinforcement learning (RL) is a technique to learn the control policy for an agent that interacts with a stochastic environment.

Model Predictive Control reinforcement-learning +1

Minimum Structural Sensor Placement for Switched Linear Time-Invariant Systems and Unknown Inputs

no code implementations28 Jul 2021 Emily A. Reed, Guilherme Ramos, Paul Bogdan, Sérgio Pequito

First, we provide necessary and sufficient conditions for their structural state and input observability that can be efficiently verified in $O((m(n+p))^2)$, where $n$ is the number of state variables, $p$ is the number of unknown inputs, and $m$ is the number of modes.

Learning Hyperbolic Representations of Topological Features

1 code implementation ICLR 2021 Panagiotis Kyriakis, Iordanis Fostiropoulos, Paul Bogdan

Learning task-specific representations of persistence diagrams is an important problem in topological data analysis and machine learning.

Image Classification Topological Data Analysis

VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text

1 code implementation28 Jan 2021 Mingxi Cheng, Shahin Nazarian, Paul Bogdan

VRoC consists of a co-train engine that trains variational autoencoders (VAEs) and rumor classification components.

General Classification

A Vertex Cut based Framework for Load Balancing and Parallelism Optimization in Multi-core Systems

no code implementations9 Oct 2020 Guixiang Ma, Yao Xiao, Theodore L. Willke, Nesreen K. Ahmed, Shahin Nazarian, Paul Bogdan

High-level applications, such as machine learning, are evolving from simple models based on multilayer perceptrons for simple image recognition to much deeper and more complex neural networks for self-driving vehicle control systems. The rapid increase in the consumption of memory and computational resources by these models demands the use of multi-core parallel systems to scale the execution of the complex emerging applications that depend on them.

Learning Information Propagation in the Dynamical Systems via Information Bottleneck Hierarchy

no code implementations ICLR 2019 Gaurav Gupta, Mohamed Ridha Znaidi, Paul Bogdan

Extracting relevant information, causally inferring and predicting the future states with high accuracy is a crucial task for modeling complex systems.

Causal Inference Clustering

Learning Latent Fractional dynamics with Unknown Unknowns

1 code implementation2 Nov 2018 Gaurav Gupta, Sergio Pequito, Paul Bogdan

Despite significant effort in understanding complex systems (CS), we lack a theory for modeling, inference, analysis and efficient control of time-varying complex networks (TVCNs) in uncertain environments.

Data-driven Perception of Neuron Point Process with Unknown Unknowns

1 code implementation2 Nov 2018 Ruochen Yang, Gaurav Gupta, Paul Bogdan

Previous research of neuron activity analysis is mainly limited with effects from the spiking history of target neuron and the interaction with other neurons in the system while ignoring the influence of unknown stimuli.

Activity Prediction Time Series Analysis

Approximate Submodular Functions and Performance Guarantees

no code implementations17 Jun 2018 Gaurav Gupta, Sergio Pequito, Paul Bogdan

Nonetheless, often we leverage the greedy algorithms used in submodular functions to determine a solution to the non-submodular functions.

Cannot find the paper you are looking for? You can Submit a new open access paper.