Research Agenda
Methods with structure
I am especially interested in methods that preserve the structure of hard combinatorial and temporal problems while still benefiting from modern data-driven techniques.
:operations-research
=machine-learning
>teaching-tools
/time-series
Researcher · Lecturer · Open-Source Builder
Optimization, learning,
and the design of
better decisions|
I work at the intersection of Operations Research, Machine Learning, and time-series forecasting, building algorithms, software, and teaching artifacts that make complex systems more understandable and more useful.
research-shell
$
pip install foreblocks
About
Academic profile
I am a researcher and lecturer interested in how rigorous optimization methods and modern learning systems can work together, both as scientific tools and as practical instruments for real decision-making.
My work moves between theory, implementation, and explanation. I care about mathematically grounded methods, but I also care about making them operational: software that runs well, interfaces that teach clearly, and systems that help people reason about difficult problems.
Across papers, libraries, and interactive materials, I aim to make advanced topics in optimization, forecasting, and machine learning feel coherent rather than fragmented, so research, teaching, and practice reinforce one another.
Teaching Lens
Clarity through interaction
As a lecturer, I value explanations that are visual, tactile, and computational, turning abstract models into things students can inspect, manipulate, and test.
Open Source
Research that ships
I see software as a research output in its own right: a way to share methods, accelerate experiments, and make academic ideas reusable outside a single paper.
Research
Themes and methods
My research sits between mathematical rigor and computational experimentation, spanning exact optimization, learning systems, and predictive modeling.
Operations Research
Branch-and-Price, decomposition methods, and scalable exact or hybrid strategies for hard optimization problems.
- Algorithm design for structured decision problems
- Exact methods combined with heuristics
- Implementations built for experimentation and reuse
Machine Learning
Learning systems designed with awareness of optimization, combinatorics, and the demands of real decision pipelines.
- Optimization-aware machine learning
- Neural methods for structured decisions
- Graph and sequence models for complex systems
Time-Series Forecasting
Deep and statistical approaches for forecasting workflows, multi-step prediction, and interpretable temporal modeling.
- Neural architectures for temporal data
- Attention mechanisms and sequence modeling
- Forecasting systems designed to scale in practice
Signals
Research topic cloud
Top Terms
Built from titles, abstracts, and keywords across available publications.
Software
Selected software
Code is part of how I research and teach. These projects range from high-performance optimization libraries to interactive explainers for advanced machine learning concepts.
B
BALDES
Branch-Cut-and-Price tooling for routing
A modern C++ implementation of bucket-graph labeling for vehicle routing problems, focused on performance, structure, and experimental flexibility.
C++
Vehicle Routing
Operations Research
F
ForeBlocks
Modular library for time-series forecasting
A flexible PyTorch-based forecasting library with multiple neural architectures, strategies, and experiment-friendly building blocks.
PyTorch
Time Series
Deep Learning
I
IPyM
Interior-point methods for linear programming
A fast C++-based interior-point method library with Python bindings designed for research workflows in linear programming.
C++
Python
Optimization
C
CHOMP
Solver design for nonlinear programming
A modular nonlinear programming solver using SQP, interior-point, and DFO-L1 strategies with an emphasis on extensibility and experimentation.
C++
NLP
SQP
Code
Open-source activity
Selected repositories drawn from GitHub, highlighting current software directions and reusable research infrastructure.
Loading…Publications
Selected publications
A concise list of recent or representative outputs, with links out to the full Google Scholar profile for citation details and a complete record.
Loading…laio@gos.ufsc.br
Best for research inquiries, course-related contact, and academic collaboration.
Send EmailGitHub
github.com/lseman
Code, experiments, optimization tooling, and research software releases.
View Profilelinkedin.com/in/lseman
A good place for professional networking, invited talks, and broader collaborations.
Connect