Research Approach Focus About Contact
Machine Learning · Reinforcement Learning · Operations Research

A research lab for systems that learn and decide.

Gauss is an independent research lab working across machine learning, reinforcement learning, and operations research, turning hard theoretical questions into algorithms and systems that learn, plan, and decide under uncertainty.

Move your cursor to reshape the landscape
What we study

We work at the meeting point of learning and optimization, developing the theory and the systems that let machines reason about uncertainty, act under constraints, and improve from experience.

01 · Research

The questions we work on.

Connected lines of inquiry spanning learning, sequential decision-making, and the mathematics that underpins them.

01

Machine Learning

Representation learning, probabilistic models, deep architectures, and the statistical foundations of generalization from data.

02

Reinforcement Learning

Sequential decision-making, policy optimization, exploration, multi-agent learning, and control under uncertainty.

03

Operations Research

Mathematical optimization, combinatorial and stochastic programming, scheduling, and large-scale decision models.

04

Decision & Uncertainty

Bayesian inference, uncertainty quantification, causal reasoning, and robust decisions under noise and partial information.

05

Learning to Optimize

Where learning meets operations research, neural combinatorial optimization, differentiable solvers, and data-driven heuristics.

Interested in a joint research direction?

Start a conversation →
02 · Approach

How we move from question to result.

Every line of work follows the same disciplined arc, posed precisely, formalized carefully, validated against evidence.

STEP 01

Pose the question

Identify the open problem, its assumptions, and what a meaningful answer would look like.

STEP 02

Formalize

Cast the problem mathematically, variables, objectives, and the structure of uncertainty.

STEP 03

Develop the method

Design algorithms and models, grounded in theory and prior work.

STEP 04

Experiment & validate

Test against benchmarks and ground truth, and quantify what was gained.

STEP 05

Share & build

Publish findings openly and turn them into systems others can use.

03 · Focus

Where our research reaches.

Representative problems and domains where our methods make a difference.

01Sequential decision-making
02Combinatorial optimization
03Learning to optimize
04Multi-agent systems
05Probabilistic forecasting
06Uncertainty quantification
07Simulation & digital twins
08Control under constraints
09Causal inference
10Reproducible ML
04 · Why Gauss

Rigor, in the open.

Gauss exists to turn hard questions in learning and optimization into theory, algorithms, and open systems that others can build on.

We work where mathematics meets computation, equally at home in a proof, a benchmark, and a production codebase.

01

Mathematical & analytical rigor

Methods chosen for correctness, not novelty, grounded in statistics and optimization theory.

02

From theory to system

Ideas that run, tested, reproducible, and built to live beyond the paper.

03

Open by default

We share methods, code, and results so the work can be checked, reused, and extended.

04

Breadth across fields

Fluent across ML, RL, and OR, one lab connecting ideas that are usually kept apart.

05

Clarity of thought

Translating between mathematical depth and real-world problems, without losing either.

05 · Contact

Tell us about a problem, a collaboration, or an idea worth exploring.

Share a short description of what you are working on. We will follow up with a considered, technical perspective and clear next steps.

contact@gauss.pt