Academic focus: Causality and robustness in statistics and data science
Research summary: I study how we can make statistical and machine learning methods more reliable for understanding cause-and-effect relationships in the real world. My work develops tools that help us answer questions like: What happens when treatments or policies change over time? How can we account for individual differences in how people or systems respond? And how do we draw valid conclusions even when our models are imperfect or data are incomplete? My research uncovers new theoretical paradigms for these problems and develops the algorithms. I am especially interested in advancing causal and robust methodology in ways that ensure that modern statistical, machine learning or AI systems can be used responsibly and effectively in high-stakes settings such as health, environment and policy, where reliable decisions matter most.
What do you like to do when you’re not working?
Outside of research, I drift with my family from city to city, following the call of fencing tournaments, a curious mix of sport, travel and chance encounters.
What brought you to Cornell CALS?
I was drawn to Cornell CALS for its strength in the quantitative sciences and its commitment to real-world challenges in biology, medicine, public health and policy. It is a place where statistical theory and data science connect directly with high-impact domains, where numbers converse with living systems and equations wander into biology and medicine. Here, abstractions return woven with the textures of reality. CALS is a meeting ground of rigor and reality, and that intersection lies at the heart of my research.
What do you think is important for people to understand about your field?
They say statistics is a museum of dead models. Yet the roots of AI and data science drink from its hidden springs, and its language still beats inside their circuits. We guard tradition and we undo it, inventing new forms, new algorithms. And in the voices of scientists, we catch questions not yet inscribed in textbooks, questions that summon new algorithms and theory.
Why did you feel inspired to pursue a career in this field?
I’ve always loved mathematics, but I also wanted my work to matter in the world outside of equations. Statistics and data science let me combine those two passions: building rigorous theory while also shaping how we answer real questions in science, medicine and policy.
What advice do you have for students interested in your field of study?
Advance AI and robotic solutions to have human level or better performances in complex agricultural tasks, such as fruit picking, crop pollination and input management, while keeping the system cost and complexity to a practically applicable level.
Learn more about Jelena from her lab website.
