research

for an extended overview, see the group webpage.

My long-term goal is to make AI more responsible — accessible, sustainable, and righteous.

As the first step toward this goal, I currently focus on AI efficiency. In particular, I aim to understand the fundamental trade-offs among three key factors:

• predictive performance
• inference cost
• training cost

I believe that such an understanding can be gained by studying the algorithmic biases inherent in machine learning algorithms.