Philip M. Long

Publications
Influence

Breast cancer classification and prognosis based on gene expression profiles from a population-based study

C. Sotiriou, Soek-Ying Neo, +7 authors E. Liu
Biology, Medicine
Proceedings of the National Academy of Sciences…
13 August 2003

Comprehensive gene expression patterns generated from cDNA microarrays were correlated with detailed clinico-pathological characteristics and clinical outcome in an unselected group of 99… Expand

1,951
89
PDF

Benign overfitting in linear regression

P. Bartlett, Philip M. Long, G'abor Lugosi, Alexander Tsigler
Computer Science, Mathematics
Proceedings of the National Academy of Sciences
26 June 2019

The phenomenon of benign overfitting is one of the key mysteries uncovered by deep learning methodology: deep neural networks seem to predict well, even with a perfect fit to noisy training data. Expand

The Relaxed Online Maximum Margin Algorithm

Y. Li, Philip M. Long
Mathematics, Computer Science
Machine Learning
29 November 1999

We describe a new incremental algorithm for training linear threshold functions: the Relaxed Online Maximum Margin Algorithm, or ROMMA. Expand

The Power of Localization for Efficiently Learning Linear Separators with Noise

P. Awasthi, Maria-Florina Balcan, Philip M. Long
Computer Science, Mathematics
J. ACM
31 July 2013

We introduce a new approach for designing computationally efficient learning algorithms that are tolerant to noise, and we demonstrate its effectiveness by designing algorithms with improved noise tolerance guarantees for learning linear separators in the presence of malicious noise or adversarial label noise. Expand

Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection

Yijun Ruan, C. L. Wei, A. Ling, V. Vega, Philip M. Long, E. Liu
Biology, Medicine
The Lancet
22 May 2003

Summary Background The cause of severe acute respiratory syndrome (SARS) has been identified as a new coronavirus. Whole genome… Expand

The Singular Values of Convolutional Layers

H. Sedghi, Vineet Gupta, Philip M. Long
Computer Science, Mathematics
ICLR
26 May 2018

We characterize the singular values of the linear transformation associated with a standard 2D multi-channel convolutional layer, enabling their efficient computation. Expand

Improved bounds on the sample complexity of learning

Y. Li, Philip M. Long, A. Srinivasan
Computer Science, Mathematics
SODA '00
1 February 2000

We present a new general upper bound on the number of examples required to estimate all of the expectations of a set of random variables uniformly well using Haussler's decision theoretic model. Expand

Random classification noise defeats all convex potential boosters

Philip M. Long, R. Servedio
Mathematics, Computer Science
ICML '08
1 March 2010

A broad class of boosting algorithms can be interpreted as performing coordinate-wise gradient descent to minimize some potential function of the margins of a data set. Expand

Comment on " 'Stemness': Transcriptional Profiling of Embryonic and Adult Stem Cells" and "A Stem Cell Molecular Signature" (I)

N. Fortunel, H. Otu, +13 authors B. Lim
Biology, Medicine
Science
17 October 2003

Ramalho-Santos et al . ([ 1 ][1]) and Ivanova et al. ([ 2 ][2]), comparing the same three “stem cells”— embryonic stem cells (ESCs); neural stem cells (NSCs), referred to as neural progenitor/stem… Expand

On the difficulty of approximately maximizing agreements

Shai Ben-David, Nadav Eiron, Philip M. Long
Computer Science, Mathematics
J. Comput. Syst. Sci.
28 June 2000

We address the computational complexity of learning in the agnostic framework. Expand

Recommended Authors