Recently added

Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games

Pipis, Charilaos (Massachusetts Institute of Technology, 2025-05)

We propose efficient no-regret learning dynamics and ellipsoid-based methods for computing linear correlated equilibria—a relaxation of correlated equilibria and a strengthening of coarse correlated equilibria—in general ...

Explaining Black-Box Classifiers by Implicitly Learning Decision Trees

Lange, Jane (Massachusetts Institute of Technology, 2025-05)

We present algorithms for finding two types of objects that explain the classification of a black-box model f : {±1}^d → {±1} on an instance x ∈ {±1}^d . The first is a certificate: a small set of x’s features that in ...

Analog On-chip Training and Inference with Non-volatile Memory Devices

Lee, Jungsoo (Massachusetts Institute of Technology, 2025-05)

As the demand for computation in neural networks continues to rise, conventional computing resources are increasingly constrained by their limited energy efficiency. One promising solution to this challenge is analog ...

DSpace@MIT

Graduate Theses: Recent submissions

Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games

Explaining Black-Box Classifiers by Implicitly Learning Decision Trees

Analog On-chip Training and Inference with Non-volatile Memory Devices

Graduate Theses: Recent submissions

Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games ﻿

Explaining Black-Box Classifiers by Implicitly Learning Decision Trees ﻿

Analog On-chip Training and Inference with Non-volatile Memory Devices ﻿

Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex Games

Explaining Black-Box Classifiers by Implicitly Learning Decision Trees

Analog On-chip Training and Inference with Non-volatile Memory Devices