The Experts below are selected from a list of 40176 Experts worldwide ranked by ideXlab platform
Rafal Weron - One of the best experts on this subject based on the ideXlab platform.
-
holtwinters Matlab Function to compute forecasts of the holt winters exponential smoothing model
HSC Software, 2017Co-Authors: Rafal WeronAbstract:[MAE,FX]=HOLTWINTERS(PARAM,S,X) returns the Mean Absolute Error (MAE) of 1-step ahead forecasts (FX) of the Holt-Winters exponential smoothing model with additive trend and additive seasonality for parameter vector PARAM = [alpha, beta, gamma], seasonality of period S and data series X.
-
deseasonalize Matlab Function to remove short and long term seasonal components new implementation
HSC Software, 2014Co-Authors: Rafal WeronAbstract:[DDATA,LTSC,STSC] = DESEASONALIZE(DATA,MET1,MET2,HOLI) returns deseasonalized data vector DDATA, long-term seasonal component LTSC and short-term seasonal component STSC obtained from the original data series DATA. Parameters MET1 and MET2 define the short- and long-term seasonal decomposition techniques, respectively. HOLI is a vector of day types, e.g. [1,2,3,4,5,6,7,8] where 8 stands for holidays. This is version 2015-02-19.
-
ltscwave Matlab Function to estimate and forecast the long term seasonal component ltsc of an electricity spot price series using wavelet based methods
HSC Software, 2013Co-Authors: Jakub Nowotarski, Jakub Tomczyk, Rafal WeronAbstract:LTSCSIN returns the long-term seasonal component (LTSC) of an electricity spot price series and its forecast up to a year ahead computed using one of the sine-based (Fourier decomposition-based) methods studied in J. Nowotarski, J. Tomczyk, R. Weron (2013), "Robust estimation and forecasting of the long-term seasonal component of electricity spot prices", Energy Economics, forthcoming (doi:10.1016/j.eneco.2013.04.004).
-
runningmedian Matlab Function to compute a running median of a time series
HSC Software, 2012Co-Authors: Rafal WeronAbstract:Y=RUNNINGMEDIAN(DATA) returns the running median of width equal to 10% of the sample size DATA. RUNNINGMEDIAN(DATA,WIDTHMED,MINRADIUS) allows to specify a different width of the running median WIDTHMED and the minimum radius of the median MINRADIUS (default: 0.5% of the sample size) to which the radius of the median is decreased at the edges.
-
e_hmm Matlab Function to calculate electromagnetic field emf intensity using a hidden markov model hmm filter
HSC Software, 2012Co-Authors: Joanna Janczura, Rafal WeronAbstract:E=E_HMM(DATA) returns the EMF intensity calculated for the EMF vector in DATA. E_HMM(DATA,PLOT,FREQ,D) additionally allows to plot (PLOT=1) the filtering results for frequencies FREQ and panel specified by D (D=0 for the central panel, D=1 for the left panel, D=2 for the right panel).
Joanna Janczura - One of the best experts on this subject based on the ideXlab platform.
-
ci_powertail Matlab Function to test for dragon kings vs black swans
HSC Software, 2012Co-Authors: Joanna Janczura, Rafal WeronAbstract:[CI_LO,CI_HI]=CI_POWERTAIL(DATA,ALPHA,TAIL) calculates confidence intervals of significance level ALPHA for a power law fitted to the right tail of the empirical distrubution Function (edf) of the observations in DATA. Only observations lying in the interval [TAIL(1)-quantile of DATA,TAIL(2)-quantile of DATA] are used to obtain the least squares fit. CI_POWERTAIL(DATA,ALPHA,TAIL,CLT) allows to choose between the exact but slower to compute (binomial law based; CLT=0) and asymptotic (Gaussian law based; CLT=1, default) confidence intervals. CI_POWERTAIL(DATA,ALPHA,TAIL,CLT,1) plots the power law and the intervals in the current figure. Observations lying outside the curves spanned by the confidence intervals are likely to be (i.e. with probability 1-ALPHA) 'dragon kings', i.e. deviations from power law events (commonly known as 'black swans'). Note, that Taleb (2007) calls these 'tractable scientifically' events 'Mandelbrotian gray swans', to distinguish them from the 'totally intractable' black swans.
-
ci_weibulltail Matlab Function to test for dragon kings in weibull type tails
HSC Software, 2012Co-Authors: Joanna Janczura, Rafal WeronAbstract:[CI_LO,CI_HI]=CI_WEIBULLTAIL(DATA,ALPHA,TAIL) calculates confidence intervals of significance level ALPHA for a Weibull law (i.e. a stretched exponential law) fitted to the right tail of the empirical distrubution Function (edf) of the observations in DATA. Only observations lying in the interval [TAIL(1)-quantile of DATA,TAIL(2)-quantile of DATA] are used to obtain the least squares fit. CI_WEIBULLTAIL(DATA,ALPHA,TAIL,CLT) allows to choose between the exact but slower to compute (binomial law based; CLT=0) and asymptotic (Gaussian law based; CLT=1, default) confidence intervals. CI_WEIBULLTAIL(DATA,ALPHA,TAIL,CLT,1) plots the Weibull law and the intervals in the current figure. Observations lying outside the curves spanned by the confidence intervals are likely to be (i.e. with probability 1-ALPHA) 'dragon kings', i.e. deviations from Weibull law.
-
e_hmm Matlab Function to calculate electromagnetic field emf intensity using a hidden markov model hmm filter
HSC Software, 2012Co-Authors: Joanna Janczura, Rafal WeronAbstract:E=E_HMM(DATA) returns the EMF intensity calculated for the EMF vector in DATA. E_HMM(DATA,PLOT,FREQ,D) additionally allows to plot (PLOT=1) the filtering results for frequencies FREQ and panel specified by D (D=0 for the central panel, D=1 for the left panel, D=2 for the right panel).
-
mrs3ir_est Matlab Function to estimate parameters of a markov regime switching mrs model with 3 independent regimes
Research Papers in Economics, 2011Co-Authors: Joanna Janczura, Rafal WeronAbstract:[KSI_TT,PARAM,P]=MRS3IR_EST(DATA,MODEL) returns smoothed inferences KSI_TT, estimated parameters PARAM and transition matrix P of a Markov regime-switching (MRS) model with 3 independent regimes: (i) an AR(1) process in the base regime X(t+1)=phi_1*X(t)+c_1+sigma_1*|X(t)|^g_1*N(0,1), (ii) a Gaussian (MODEL='G'), lognormal ('LN'), Pareto ('P'), Weibull ('W') or exponential ('E') distributed spike regime, (iii) and a shifted 'inverse lognormal' price drop regime, fitted to time series DATA. The first column (KSI_TT) or row (PARAM, P) contains results for the base regime, the second column/row for the spike regime and the third column/row for the drop regime.
-
ps2r_est Matlab Function to estimate parameters of a 2 regime parameter switching ps model
Research Papers in Economics, 2011Co-Authors: Joanna Janczura, Rafal WeronAbstract:[KSI_TT,PARAM,P]=PS2R_EST(DATA) returns smoothed inferences KSI_TT, estimated parameters PARAM and transition matrix P of a 2-regime parameter switching (PS) model, i.e. a 2-regime Markov regime-switching (MRS) model with both regimes driven by AR(1) processes of the form: X(t+1)=phi_i*X(t)+c_i+sigma_i*|X(t)|^g_i*N(0,1). The first column (KSI_TT) or row (PARAM, P) contains results for the base regime and the second column/row for the spike regime.
Pranesh Srikara - One of the best experts on this subject based on the ideXlab platform.
-
Random Matrices Generating Large Growth in LU Factorization with Pivoting
2020Co-Authors: Higham, Desmond J., Higham, Nicholas J., Pranesh SrikaraAbstract:We identify a class of random, dense $n\times n$ matrices for which LU factorization with any form of pivoting produces a growth factor typically of size at least $n/(4 \log n)$ for large $n$. The condition number of the matrices can be arbitrarily chosen and large growth also happens for the transpose. No previous matrices with all these properties were known. The matrices can be generated by the Matlab Function \verb"gallery('randsvd',..)", and they are formed as the product of two random orthogonal matrices from the Haar distribution with a diagonal matrix having only one diagonal entry different from $1$, which lies between $0$ and $1$ (the ``one small singular value'' case). Our explanation for the large growth uses the fact that the maximum absolute value of any element of a Haar distributed orthogonal matrix tends to be relatively small for large $n$. We verify the behavior numerically, finding that for partial pivoting the actual growth is significantly larger than the lower bound, and much larger than the growth observed for random matrices with elements from the uniform $[0,1$] or standard normal distributions. We show more generally that a rank-$1$ perturbation to an orthogonal matrix producing large growth for any form of pivoting also generates large growth under reasonable assumptions. Finally, we demonstrate that GMRES-based iterative refinement can provide stable solutions to $Ax = b$ when large growth occurs in low precision LU factors, even when standard iterative refinement cannot
-
Random Matrices Generating Large Growth in LU Factorization with Pivoting
2020Co-Authors: Higham, Desmond J., Higham, Nicholas J., Pranesh SrikaraAbstract:We identify a class of random, dense $n\times n$ matrices for which LU factorization with any form of pivoting produces a growth factor of at least $n/(4 \log n)$ for large $n$ with high probability. The condition number of the matrices can be arbitrarily chosen and large growth also happens for the transpose. No previous matrices with all these properties were known. The matrices can be generated by the Matlab Function \verb"gallery('randsvd',..)", and they are formed as the product of two random orthogonal matrices from the Haar distribution with a diagonal matrix having only one diagonal entry different from $1$, which lies between $0$ and $1$ (the ``one small singular value'' case). Our explanation for the large growth uses the fact that the maximum absolute value of any element of a Haar distributed orthogonal matrix tends to be relatively small for large $n$. We verify the behavior numerically, finding that for partial pivoting the actual growth is significantly larger than the lower bound, and much larger than the growth observed for random matrices with elements from the uniform $[0,1$] or standard normal distributions. We show more generally that a rank-$1$ perturbation to an orthogonal matrix producing large growth for any form of pivoting also generates large growth under reasonable assumptions. Finally, we demonstrate that GMRES-based iterative refinement can provide stable solutions to $Ax = b$ when large growth occurs in low precision LU factors, even when standard iterative refinement cannot
-
SIMULATING LOW PRECISION FLOATING-POINT ARITHMETIC
2019Co-Authors: Higham, Nicholas J., Pranesh SrikaraAbstract:The half precision (fp16) floating-point format, defined in the 2008 revision of the IEEE standard for floating-point arithmetic, and a more recently proposed half precision format bfloat16, are increasingly available in GPUs and other accelerators. While the support for low precision arithmetic is mainly motivated by machine learning applications, general purpose numerical algorithms can benefit from it, too, gaining in speed, energy usage, and reduced communication costs. Since the appropriate hardware is not always available, and one may wish to experiment with new arithmetics not yet implemented in hardware, software simulations of low precision arithmetic are needed. We discuss how to simulate low precision arithmetic using arithmetic of higher precision. We examine the correctness of such simulations and explain via rounding error analysis why a natural method of simulation can provide results that are more accurate than actual computations at low precision. We provide a Matlab Function chop that can be used to efficiently simulate fp16, bfloat16, and other low precision arithmetics, with or without the representation of subnormal numbers and with the options of round to nearest, directed rounding, stochastic rounding, and random bit flips in the significand. We demonstrate the advantages of this approach over defining a new Matlab class and overloading operators
-
SIMULATING LOW PRECISION FLOATING-POINT ARITHMETIC
2019Co-Authors: Higham, Nicholas J., Pranesh SrikaraAbstract:The half precision (fp16) floating-point format, defined in the 2008 revision of the IEEE standard for floating-point arithmetic, and a more recently proposed half precision format bfloat16, are increasingly available in GPUs and other accelerators. While the support for low precision arithmetic is mainly motivated by machine learning applications, general purpose numerical algorithms can benefit from it, too, gaining in speed, energy usage, and reduced communication costs. Since the appropriate hardware is not always available, and one may wish to experiment with new arithmetics not yet implemented in hardware, software simulations of low precision arithmetic are needed. We discuss how to simulate low precision arithmetic using arithmetic of higher precision. We examine the correctness of such simulations and explain via rounding error analysis why a natural method of simulation can provide results that are more accurate than actual computations at low precision. We provide a Matlab Function chop that can be used to efficiently simulate fp16 and bfloat16 arithmetics, with or without the representation of subnormal numbers and with the options of round to nearest, directed rounding, stochastic rounding, and random bit flips in the significand. We demonstrate the advantages of this approach over defining a new Matlab class and overloading operators
Rafał Weron - One of the best experts on this subject based on the ideXlab platform.
-
SCAR: Matlab Function to compute day-ahead predictions of the electricity spot price using the Seasonal Component AutoRegressive (SCAR) model
2016Co-Authors: Jakub Nowotarski, Rafał WeronAbstract:SCAR computes day-ahead predictions of the electricity spot price given historical prices and forecasted loads using the Seasonal Component AutoRegressive (SCAR) model introduced in J. Nowotarski, R. Weron (2016) "On the importance of the long-term seasonal component in day-ahead electricity price forecasting", Energy Economics 57, 228-235 (http://dx.doi.org/10.1016/j.eneco.2016.05.009), as well as the classical AR model.
-
AWC_HURST: Matlab Function to compute the Hurst exponent using the Average Wavelet Coefficient (AWC) method
2014Co-Authors: Rafał WeronAbstract:H = AWC_HURST(DATA) returns the Hurst exponent H for sample DATA using the Average Wavelet Coefficient (AWC) method of Simonsen et al. (1998). H = AWC_HURST(DATA,N,T,WAVEMODE,WAVE) allows to specify the decomposition level (default: N is the largest power of two such that 2^N is not greater than the sample size), the vector of powers of two used in the AWC regression (default: T = 1:(N-1)), the discrete wavelet transform extension mode (default: WAVEMODE = 'per'; see also dwtmode.m) and the wavelet type (default: WAVE = 'db24'). If there are no output parameters, the AWC statistics is automatically plotted against the powers of two on a loglog paper and the results of the analysis are displayed in the command window.
-
LTSCWAVE: Matlab Function to estimate and forecast the long-term seasonal component (LTSC) of an electricity spot price series using wavelet-based methods
2013Co-Authors: Jakub Nowotarski, Jakub Tomczyk, Rafał WeronAbstract:LTSCWAVE returns the long-term seasonal component (LTSC) of an electricity spot price series and its forecast up to a year ahead computed using one of the wavelet-based methods studied in J. Nowotarski, J. Tomczyk, R. Weron (2013), "Robust estimation and forecasting of the long-term seasonal component of electricity spot prices", Energy Economics, forthcoming (doi:10.1016/j.eneco.2013.04.004).
-
DESEASONALIZE: Matlab Function to remove short and long term seasonal components
Statistical Software Components, 2010Co-Authors: Rafał WeronAbstract:DESEASONALIZE returns deseasonalized time series and the short- (STSC) and long-term seasonal components (LTSC). The LTSC is obtained either through wavelet decomposition or by fitting a sinusoid. The STSC is extracted by finding the mean or median periodic component. The original and deseasonalized time series can be plotted together with their periodograms.
-
PERIODOG: Matlab Function to compute and plot the periodogram of a time series
2006Co-Authors: Rafał WeronAbstract:PERIODOG(X) returns the POWER and FREQuency such that PLOT(FREQ,POWER) is the periodogram (estimate of the spectral density). Period (i.e. 1/FREQ) MAXP of the maximum value of the periodogram is also returned.
Higham, Nicholas J. - One of the best experts on this subject based on the ideXlab platform.
-
Random Matrices Generating Large Growth in LU Factorization with Pivoting
2020Co-Authors: Higham, Desmond J., Higham, Nicholas J., Pranesh SrikaraAbstract:We identify a class of random, dense $n\times n$ matrices for which LU factorization with any form of pivoting produces a growth factor typically of size at least $n/(4 \log n)$ for large $n$. The condition number of the matrices can be arbitrarily chosen and large growth also happens for the transpose. No previous matrices with all these properties were known. The matrices can be generated by the Matlab Function \verb"gallery('randsvd',..)", and they are formed as the product of two random orthogonal matrices from the Haar distribution with a diagonal matrix having only one diagonal entry different from $1$, which lies between $0$ and $1$ (the ``one small singular value'' case). Our explanation for the large growth uses the fact that the maximum absolute value of any element of a Haar distributed orthogonal matrix tends to be relatively small for large $n$. We verify the behavior numerically, finding that for partial pivoting the actual growth is significantly larger than the lower bound, and much larger than the growth observed for random matrices with elements from the uniform $[0,1$] or standard normal distributions. We show more generally that a rank-$1$ perturbation to an orthogonal matrix producing large growth for any form of pivoting also generates large growth under reasonable assumptions. Finally, we demonstrate that GMRES-based iterative refinement can provide stable solutions to $Ax = b$ when large growth occurs in low precision LU factors, even when standard iterative refinement cannot
-
Random Matrices Generating Large Growth in LU Factorization with Pivoting
2020Co-Authors: Higham, Desmond J., Higham, Nicholas J., Pranesh SrikaraAbstract:We identify a class of random, dense $n\times n$ matrices for which LU factorization with any form of pivoting produces a growth factor of at least $n/(4 \log n)$ for large $n$ with high probability. The condition number of the matrices can be arbitrarily chosen and large growth also happens for the transpose. No previous matrices with all these properties were known. The matrices can be generated by the Matlab Function \verb"gallery('randsvd',..)", and they are formed as the product of two random orthogonal matrices from the Haar distribution with a diagonal matrix having only one diagonal entry different from $1$, which lies between $0$ and $1$ (the ``one small singular value'' case). Our explanation for the large growth uses the fact that the maximum absolute value of any element of a Haar distributed orthogonal matrix tends to be relatively small for large $n$. We verify the behavior numerically, finding that for partial pivoting the actual growth is significantly larger than the lower bound, and much larger than the growth observed for random matrices with elements from the uniform $[0,1$] or standard normal distributions. We show more generally that a rank-$1$ perturbation to an orthogonal matrix producing large growth for any form of pivoting also generates large growth under reasonable assumptions. Finally, we demonstrate that GMRES-based iterative refinement can provide stable solutions to $Ax = b$ when large growth occurs in low precision LU factors, even when standard iterative refinement cannot
-
SIMULATING LOW PRECISION FLOATING-POINT ARITHMETIC
2019Co-Authors: Higham, Nicholas J., Pranesh SrikaraAbstract:The half precision (fp16) floating-point format, defined in the 2008 revision of the IEEE standard for floating-point arithmetic, and a more recently proposed half precision format bfloat16, are increasingly available in GPUs and other accelerators. While the support for low precision arithmetic is mainly motivated by machine learning applications, general purpose numerical algorithms can benefit from it, too, gaining in speed, energy usage, and reduced communication costs. Since the appropriate hardware is not always available, and one may wish to experiment with new arithmetics not yet implemented in hardware, software simulations of low precision arithmetic are needed. We discuss how to simulate low precision arithmetic using arithmetic of higher precision. We examine the correctness of such simulations and explain via rounding error analysis why a natural method of simulation can provide results that are more accurate than actual computations at low precision. We provide a Matlab Function chop that can be used to efficiently simulate fp16, bfloat16, and other low precision arithmetics, with or without the representation of subnormal numbers and with the options of round to nearest, directed rounding, stochastic rounding, and random bit flips in the significand. We demonstrate the advantages of this approach over defining a new Matlab class and overloading operators
-
SIMULATING LOW PRECISION FLOATING-POINT ARITHMETIC
2019Co-Authors: Higham, Nicholas J., Pranesh SrikaraAbstract:The half precision (fp16) floating-point format, defined in the 2008 revision of the IEEE standard for floating-point arithmetic, and a more recently proposed half precision format bfloat16, are increasingly available in GPUs and other accelerators. While the support for low precision arithmetic is mainly motivated by machine learning applications, general purpose numerical algorithms can benefit from it, too, gaining in speed, energy usage, and reduced communication costs. Since the appropriate hardware is not always available, and one may wish to experiment with new arithmetics not yet implemented in hardware, software simulations of low precision arithmetic are needed. We discuss how to simulate low precision arithmetic using arithmetic of higher precision. We examine the correctness of such simulations and explain via rounding error analysis why a natural method of simulation can provide results that are more accurate than actual computations at low precision. We provide a Matlab Function chop that can be used to efficiently simulate fp16 and bfloat16 arithmetics, with or without the representation of subnormal numbers and with the options of round to nearest, directed rounding, stochastic rounding, and random bit flips in the significand. We demonstrate the advantages of this approach over defining a new Matlab class and overloading operators