Call For Papers

Call For Papers

2026 International Conference on Computational Theory and Machine Learning (CTML2026) will bring together leading researchers, engineers and scientists in the domain of interest from around the world.
The topics of interest for submission include, but are not limited to:

Track 1: Foundations of Computational Learning

Statistical Learning Theory and Generalization
Computational Complexity of Learning
Online Learning and Regret Analysis
Learning Dynamics and Convergence
Scaling Laws and Emergent Behavior in Large Models
PAC-Bayes Theory and Algorithmic Stability

Track 2: Deep Learning Theory and Neural Architectures

Expressivity and Capacity of Neural Networks
Theoretical Analysis of Transformers and Foundation Models
Neural Network Optimization Landscapes
Overparameterization and Double Descent
Implicit Regularization and Bias of Gradient Methods
Mechanistic Interpretability and Model Internals
Physics-Informed Neural Networks and Neural Operators

Track 3: Optimization and Algorithms for Machine Learning

Convex and Non-Convex Optimization
Evolutionary Algorithms and Metaheuristics
Combinatorial Optimization in Learning
Surrogate-Assisted and Expensive Optimization
Optimization for Resource-Constrained Settings
Federated Learning and Distributed Optimization
Multi-Objective Optimization in ML Systems

Track 4: Graph Theory, Combinatorics, and Learning on Structures

Graph Neural Networks Theory
Spectral Graph Theory and Applications
Algorithmic Graph Theory and Network Analysis
Combinatorial Optimization with Learning
Random Graphs and Probabilistic Methods
Geometric Deep Learning
Learning on Manifolds and Non-Euclidean Data

Track 5: Trustworthy and Explainable AI

Causal Inference and Discovery
Explainability and Interpretability
Robustness, Uncertainty, and Calibration
Privacy and Fairness in Machine Learning
Adversarial Machine Learning
Distribution Shift and Domain Generalization
Safety and Alignment of AI Systems

Track 6: AI for Scientific Discovery and Emerging Frontiers

AI for Scientific Discovery
Quantum Machine Learning
Symbolic Regression and Scientific Law Discovery
AI-Accelerated Scientific Computing
Multi-Modal Learning and Fusion
Computational Biology and AI for Healthcare
Climate Modeling and Environmental AI

Track 7: Efficient and Scalable Machine Learning Systems

Model Compression and Knowledge Distillation
Quantization and Pruning
Neural Architecture Search
Edge AI and TinyML
Green AI and Energy-Efficient Learning
Large-Scale Training Systems
ML Compilers and Hardware-Software Co-Design