Timezone: »

Just-In-Time Learning for Fast and Flexible Inference
S. M. Ali Eslami · Daniel Tarlow · Pushmeet Kohli · John Winn

Thu Dec 11 11:00 AM -- 03:00 PM (PST) @ Level 2, room 210D #None

Much of research in machine learning has centered around the search for inference algorithms that are both general-purpose and efficient. The problem is extremely challenging and general inference remains computationally expensive. We seek to address this problem by observing that in most specific applications of a model, we typically only need to perform a small subset of all possible inference computations. Motivated by this, we introduce just-in-time learning, a framework for fast and flexible inference that learns to speed up inference at run-time. Through a series of experiments, we show how this framework can allow us to combine the flexibility of sampling with the efficiency of deterministic message-passing.

Author Information

Ali Eslami (Microsoft Research)
Daniel Tarlow (Google Brain)
Pushmeet Kohli (Microsoft Research)
John Winn (Microsoft Research)

More from the Same Authors