TY - GEN

T1 - Ambiguous model learning made unambiguous with 1/f priors

AU - Atwal, G. S.

AU - Bialek, William

PY - 2004/1/1

Y1 - 2004/1/1

N2 - What happens to the optimal interpretation of noisy data when there exists more than one equally plausible interpretation of the data? In a Bayesian modellearning framework the answer depends on the prior expectations of the dynamics of the model parameter that is to be inferred from the data. Local time constraints on the priors are insufficient to pick one interpretation over another. On the other hand, nonlocal time constraints, induced by a 1/f noise spectrum of the priors, is shown to permit learning of a specific model parameter even when there are infinitely many equally plausible interpretations of the data. This transition is inferred by a remarkable mapping of the model estimation problem to a dissipative physical system, allowing the use of powerful statistical mechanical methods to uncover the transition from indeterminate to determinate model learning.

AB - What happens to the optimal interpretation of noisy data when there exists more than one equally plausible interpretation of the data? In a Bayesian modellearning framework the answer depends on the prior expectations of the dynamics of the model parameter that is to be inferred from the data. Local time constraints on the priors are insufficient to pick one interpretation over another. On the other hand, nonlocal time constraints, induced by a 1/f noise spectrum of the priors, is shown to permit learning of a specific model parameter even when there are infinitely many equally plausible interpretations of the data. This transition is inferred by a remarkable mapping of the model estimation problem to a dissipative physical system, allowing the use of powerful statistical mechanical methods to uncover the transition from indeterminate to determinate model learning.

UR - http://www.scopus.com/inward/record.url?scp=33444471980&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33444471980&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33444471980

SN - 0262201526

SN - 9780262201520

T3 - Advances in Neural Information Processing Systems

BT - Advances in Neural Information Processing Systems 16 - Proceedings of the 2003 Conference, NIPS 2003

PB - Neural information processing systems foundation

T2 - 17th Annual Conference on Neural Information Processing Systems, NIPS 2003

Y2 - 8 December 2003 through 13 December 2003

ER -