Timezone: »

Active Learning with Oracle Epiphany
Tzu-Kuo Huang · Lihong Li · Ara Vartanian · Saleema Amershi · Jerry Zhu

Mon Dec 05 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #43

We present a theoretical analysis of active learning with more realistic interactions with human oracles. Previous empirical studies have shown oracles abstaining on difficult queries until accumulating enough information to make label decisions. We formalize this phenomenon with an “oracle epiphany model” and analyze active learning query complexity under such oracles for both the realizable and the agnos- tic cases. Our analysis shows that active learning is possible with oracle epiphany, but incurs an additional cost depending on when the epiphany happens. Our results suggest new, principled active learning approaches with realistic oracles.

Author Information

Tzu-Kuo Huang (Uber Advanced Technologies Center)
Lihong Li (Microsoft Research)
Ara Vartanian (University of Wisconsin-Madison)
Saleema Amershi (Microsoft)
Jerry Zhu (University of Wisconsin-Madison)

More from the Same Authors