Comprehensive Benchmarking of Deep Learning Optimizers: A Multi-Architecture Analysis
V Gupta, R Lal, S Das, N Tyagi, K Kunal
9th International Conference on Micro-electronics and Telecommunication • 2025
View Paper
Naman Tyagi
Undergraduate Student in Computer Science
Investigating the core principles of learning in neural networks, focusing on how efficiency through compression and sparsity reshapes our understanding of generalization and robustness in models.
About
I am currently pursuing my Bachelor's in Computer Science and Engineering at Amity University, with expected graduation in 2026. My academic journey has been focused on deep learning, model optimization, and computational efficiency in neural networks.
My research explores the intersection of model efficiency and practical applications in computer vision and natural language processing. I'm passionate about developing optimized deep learning systems that balance performance with computational constraints, working on problems ranging from image forgery detection to mathematical reasoning in language models.
Beyond my core research interests, I'm developing a growing curiosity for communication theory, particularly in multi-agent systems contexts, and am actively learning about information exchange and coordination mechanisms between computational entities.
Looking ahead, I plan to pursue a Ph.D. and build a career in academia, where I can contribute to advancing computing research while making quality education accessible through knowledge sharing.
Interests
•Efficient Machine Learning
•Model Compression
•Structured Sparsity
•Robustness and Generalization
•Optimization Dynamics in Neural Networks
Publications
MEMO Benchmark: Guiding Optimization Trade-offs in Deep Neural Networks
N Tyagi, S Das, Kunal, V Gupta, M Kakkar
International Hybrid Conference on Decision Aid Sciences and Applications • 2025
View PaperMulti-Domain Information-Theoretic Features and Kolmogorov Complexity for Lightweight Image Splicing Detection
N Tyagi, RC Joshi, S Das, Kunal, S Vojtech, J Stepan, MK Dutta
17th International Congress on Ultra Modern Telecommunications and Control • 2025
View PaperReinforcement Learning for Mathematical Reasoning in Small-Scale Language Models with Structured Policy Optimization
N Tyagi, RC Joshi, S Das, P Sikora, V Myska, MK Dutta
17th International Congress on Ultra Modern Telecommunications and Control • 2025
View PaperMulti Stream Attention Networks with Adaptive Syntactic-Emotional Fusion for Sentiment Analysis
N Mishra, A Gupta, S Mala, S Das, N Tyagi, S Bhardwaj, NC Debnath, ...
International Journal of Computers and Their Applications • 2025
View PaperAI-Enabled Skin Disease Identification and Diagnosis Robot
R Lal, A Sharma, Kunal, N Tyagi, S Das, V Gupta, M Singh, A Chopra, ...
IN Patent 454778-001 • 2025
View PaperProjects
ConvNet Library
An educational project implementing a tiny convolutional neural networks library.
PythonPyTorch
Visit Project →Blog
Thoughts on Machine Learning, usually writups about theoretical topics I find interesting.
ML Theory15 min read
But what does it mean for something to be learnable?
Exploring what learnability means in the context of machine learning, specifically deep learning.
ML Theory15 min read
But what does it mean for a network to generalize?
Explore the concept of generalization in neural networks and its implications for model performance.