Generalization bounds for learning with linear, polygonal, quadratic and conic side knowledge
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 605478392 | ||
| 003 | CHVBK | ||
| 005 | 20210128100405.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20150901xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s10994-014-5478-4 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s10994-014-5478-4 | ||
| 245 | 0 | 0 | |a Generalization bounds for learning with linear, polygonal, quadratic and conic side knowledge |h [Elektronische Daten] |c [Theja Tulabandhula, Cynthia Rudin] |
| 520 | 3 | |a In this paper, we consider a supervised learning setting where side knowledge is provided about the labels of unlabeled examples. The side knowledge has the effect of reducing the hypothesis space, leading to tighter generalization bounds, and thus possibly better generalization. We consider several types of side knowledge, the first leading to linear and polygonal constraints on the hypothesis space, the second leading to quadratic constraints, and the last leading to conic constraints. We show how different types of domain knowledge can lead directly to these kinds of side knowledge. We prove bounds on complexity measures of the hypothesis space for quadratic and conic side knowledge, and show that these bounds are tight in a specific sense for the quadratic case. | |
| 540 | |a The Author(s), 2014 | ||
| 690 | 7 | |a Statistical learning theory |2 nationallicence | |
| 690 | 7 | |a Generalization bounds |2 nationallicence | |
| 690 | 7 | |a Rademacher complexity |2 nationallicence | |
| 690 | 7 | |a Covering numbers, constrained linear function classes |2 nationallicence | |
| 690 | 7 | |a Side knowledge |2 nationallicence | |
| 700 | 1 | |a Tulabandhula |D Theja |u Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 02139, Cambridge, MA, USA |4 aut | |
| 700 | 1 | |a Rudin |D Cynthia |u MIT Sloan School of Management, Massachusetts Institute of Technology, 02139, Cambridge, MA, USA |4 aut | |
| 773 | 0 | |t Machine Learning |d Springer US; http://www.springer-ny.com |g 100/2-3(2015-09-01), 183-216 |x 0885-6125 |q 100:2-3<183 |1 2015 |2 100 |o 10994 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s10994-014-5478-4 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s10994-014-5478-4 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Tulabandhula |D Theja |u Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 02139, Cambridge, MA, USA |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Rudin |D Cynthia |u MIT Sloan School of Management, Massachusetts Institute of Technology, 02139, Cambridge, MA, USA |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t Machine Learning |d Springer US; http://www.springer-ny.com |g 100/2-3(2015-09-01), 183-216 |x 0885-6125 |q 100:2-3<183 |1 2015 |2 100 |o 10994 | ||