Poster
More Supervision, Less Computation: Statistical-Computational Tradeoffs in Weakly Supervised Learning
Xinyang Yi · Zhaoran Wang · Zhuoran Yang · Constantine Caramanis · Han Liu

Mon Dec 5th 06:00 -- 09:30 PM @ Area 5+6+7+8 #114 #None
We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability $1-\alpha$. Although there exist numerous algorithms for this problem, it remains theoretically unexplored how the statistical accuracies and computational efficiency of these algorithms depend on the degree of supervision, which is quantified by $\alpha$. In this paper, we characterize the effect of $\alpha$ by establishing the information-theoretic and computational boundaries, namely, the minimax-optimal statistical accuracy that can be achieved by all algorithms, and polynomial-time algorithms under an oracle computational model. For small $\alpha$, our result shows a gap between these two boundaries, which represents the computational price of achieving the information-theoretic boundary due to the lack of supervision. Interestingly, we also show that this gap narrows as $\alpha$ increases. In other words, having more supervision, i.e., more correct labels, not only improves the optimal statistical accuracy as expected, but also enhances the computational efficiency for achieving such accuracy.

Author Information

Xinyang Yi (UT Austin)
Zhaoran Wang (Princeton University)
Zhuoran Yang (Princeton University)
Constantine Caramanis (UT Austin)
Han Liu (Tencent AI Lab)

More from the Same Authors