1 code implementation • 27 May 2022 • Sabina J. Sloman, Daniel M. Oppenheimer, Stephen B. Broomell, Cosma Rohilla Shalizi
We show that active learning bias can also afflict Bayesian adaptive experimental design, depending on model misspecification.
1 code implementation • 6 Dec 2019 • Octavio César Mesner, Cosma Rohilla Shalizi
One reason conditional mutual information is not more widely used for these tasks is the lack of estimators which can handle combinations of continuous and discrete random variables, common in applications.
Statistics Theory Methodology Statistics Theory
no code implementations • 8 Jun 2015 • George D. Montanez, Cosma Rohilla Shalizi
Spatio-temporal data is intrinsically high dimensional, so unsupervised modeling is only feasible if we can exploit structure in the process.
no code implementations • NeurIPS 2013 • Cosma Rohilla Shalizi, Aryeh Kontorovich
We informally call a stochastic process learnable if it admits a generalization error approaching zero in probability for any concept class with finite VC-dimension (IID processes are the simplest example).
no code implementations • 3 Dec 2012 • Daniel J. McDonald, Cosma Rohilla Shalizi, Mark Schervish
We derive generalization error bounds for traditional time-series forecasting models.
no code implementations • 15 Nov 2012 • Georg M. Goerg, Cosma Rohilla Shalizi
We introduce 'mixed LICORS', an algorithm for learning nonlinear, high-dimensional dynamics from spatio-temporal data, suitable for both prediction and simulation.
no code implementations • 17 Jul 2012 • Xiaoran Yan, Cosma Rohilla Shalizi, Jacob E. Jensen, Florent Krzakala, Cristopher Moore, Lenka Zdeborova, Pan Zhang, Yaojia Zhu
We present the first principled and tractable approach to model selection between standard and degree-corrected block models, based on new large-graph asymptotics for the distribution of log-likelihood ratios under the stochastic block model, finding substantial departures from classical results for sparse graphs.
no code implementations • 3 Jun 2011 • Daniel J. McDonald, Cosma Rohilla Shalizi
We show how to control the generalization error of time series models wherein past values of the outcome are used to predict future values.
7 code implementations • 7 Jun 2007 • Aaron Clauset, Cosma Rohilla Shalizi, M. E. J. Newman
Power-law distributions occur in many situations of scientific interest and have significant consequences for our understanding of natural and man-made phenomena.
Data Analysis, Statistics and Probability Disordered Systems and Neural Networks Applications Methodology
2 code implementations • 6 Jun 2004 • Cosma Rohilla Shalizi, Kristina Lisa Shalizi
We present a new method for nonlinear prediction of discrete random sequences under minimal structural assumptions.
no code implementations • 9 Jul 2003 • Cosma Rohilla Shalizi
In this chapter, I review the main methods and techniques of complex systems science.
Adaptation and Self-Organizing Systems Statistical Mechanics Chaotic Dynamics Cellular Automata and Lattice Gases Data Analysis, Statistics and Probability Quantitative Methods