root


Mode:

Legend:

Added
Modified
Copied or renamed
Rev Chgset Date Author Log Message
(edit) @293 [293] 06/09/11 23:15:34 dsimcha Better loop unrolling: Speed up ILP optimized functions ~10%.
(edit) @292 [292] 05/26/11 09:09:31 dsimcha Add dirichlet distribution.
(edit) @291 [291] 05/25/11 22:18:41 dsimcha Docs
(edit) @290 [290] 05/25/11 22:17:37 dsimcha Add beta distribution to dstats.distrib, clean up dstatsEnforce line …
(edit) @289 [289] 05/18/11 18:58:38 dsimcha T, F tests should work even when a category only has one sample.
(edit) @288 [288] 05/14/11 12:21:49 dsimcha Minor updates for 2.053.
(edit) @287 [287] 03/16/11 09:14:55 dsimcha These should be static to work around bugs in GDC.
(edit) @286 [286] 03/12/11 11:27:44 dsimcha Fix singularness stuff.
(edit) @285 [285] 03/07/11 22:22:06 dsimcha This should be even better numerically.
(edit) @284 [284] 03/07/11 20:07:05 dsimcha This should help w/ numerical stability a little.
(edit) @283 [283] 03/04/11 22:38:40 dsimcha Should be the last of the ridge regression numerical issues.
(edit) @282 [282] 03/04/11 09:30:28 dsimcha This should fix some of the convergence failures related to oscillation …
(edit) @281 [281] 03/03/11 20:38:16 dsimcha These should use relative error. This also fixes some convergence issues.
(edit) @280 [280] 03/03/11 18:40:05 dsimcha This is mature enough to be exposed.
(edit) @279 [279] 03/03/11 18:37:29 dsimcha Fix convergence issues.
(edit) @278 [278] 03/03/11 18:36:55 dsimcha Nasty pointer bug that's only predictably reproducible on 64.
(edit) @277 [277] 02/22/11 09:07:54 dsimcha Make sure alignBytes is the right width for bit twiddling to work on 64.
(edit) @276 [276] 02/21/11 20:28:58 dsimcha Make TempAlloc? use the C heap. Remove excessively zealous nothrow's …
(edit) @275 [275] 02/21/11 00:15:46 dsimcha --
(edit) @274 [274] 02/20/11 19:44:08 dsimcha This should really be static.
(edit) @273 [273] 02/19/11 18:45:07 dsimcha Work around compiler bugs.
(edit) @272 [272] 02/19/11 12:12:15 dsimcha Update appendDelOld to work with new array appending scheme.
(edit) @271 [271] 02/19/11 10:29:54 dsimcha ...and don't leak memory while doing it.
(edit) @270 [270] 02/19/11 10:28:48 dsimcha Fall back to solving directly in pathological cases.
(edit) @269 [269] 02/15/11 21:06:02 dsimcha Recycle starting values.
(edit) @268 [268] 02/13/11 00:41:32 dsimcha Docs.
(edit) @267 [267] 02/13/11 00:41:10 dsimcha Lasso and efficient p >> n ridge regression.
(edit) @266 [266] 02/12/11 19:18:03 dsimcha Mostly WIP, some trivial fixes.
(edit) @265 [265] 02/10/11 21:58:30 dsimcha WIP
(edit) @264 [264] 02/08/11 23:26:22 dsimcha Use Cholesky decomposition instead of Gaussian elimination. About 3x …
(edit) @263 [263] 02/08/11 08:45:30 dsimcha Minor fixes and work in progress.
(edit) @262 [262] 02/05/11 23:56:47 dsimcha docs
(edit) @261 [261] 02/05/11 23:20:11 dsimcha --
(edit) @260 [260] 02/05/11 20:38:42 dsimcha Docs.
(edit) @259 [259] 02/05/11 20:37:55 dsimcha Massively overhaul PCA module.
(edit) @258 [258] 02/04/11 23:02:13 dsimcha Speed up matrix ops for regression.
(edit) @257 [257] 02/04/11 20:32:43 dsimcha Some obvious in hindsight cache optimizations.
(edit) @256 [256] 02/04/11 08:59:12 dsimcha Duh...Better yet, go with the grain for better cache performance.
(edit) @255 [255] 02/04/11 08:46:14 dsimcha Optimization: Compute half the matrix, then symmetrize, rather than …
(edit) @254 [254] 02/03/11 00:24:05 dsimcha One more bug fix.
(edit) @253 [253] 02/02/11 23:42:36 dsimcha Fix a major and amazingly well hidden memory recycling bug.
(edit) @252 [252] 02/02/11 22:55:22 dsimcha Add logistic ridge, redesign linear ridge.
(edit) @251 [251] 02/01/11 23:32:38 dsimcha Don't intermingle ridge w/ logistic.
(edit) @250 [250] 02/01/11 23:28:54 dsimcha docs
(edit) @249 [249] 02/01/11 23:27:23 dsimcha Add ridge regression, a few small misc, cleanups.
(edit) @248 [248] 01/27/11 09:40:43 dsimcha Fix some minor silliness.
(edit) @247 [247] 01/26/11 21:41:04 dsimcha docs
(edit) @246 [246] 01/26/11 21:33:53 dsimcha Add full hypothesis testing for logistic regression.
(edit) @245 [245] 01/26/11 09:39:19 dsimcha Fix NaN/degenerate case handling in logisticRegressBeta.
(edit) @244 [244] 01/24/11 22:40:33 dsimcha These should actually return NaNs?.
(edit) @243 [243] 01/24/11 22:37:27 dsimcha Fix numerical fuzz issues.
(edit) @242 [242] 01/23/11 12:58:07 dsimcha Added p-value stuff for DenseInfoTheory/?
(edit) @241 [241] 01/22/11 21:56:22 dsimcha Added DenseInfoTheory?.
(edit) @240 [240] 01/22/11 19:07:16 dsimcha Add candydoc that I accidentally removed.
(edit) @239 [239] 01/22/11 19:05:23 dsimcha More info theory/gtest merging improvements.
(edit) @238 [238] 01/22/11 16:23:53 dsimcha Added hypothesis testing for mutual information.
(edit) @237 [237] 01/22/11 11:27:48 dsimcha Fix g-test to work in cases w/ zero observations.
(edit) @236 [236] 01/08/11 09:37:37 dsimcha Improve error messages.
(edit) @235 [235] 12/22/10 20:38:56 dsimcha Forgot to add back a few pure nothrows.
(edit) @234 [234] 12/22/10 20:35:18 dsimcha 2.051 updates. This breaks all earlier versions of DMD because I dumped …
(edit) @233 [233] 12/13/10 19:51:00 dsimcha Exception vs. NaN convention.
(edit) @232 [232] 11/21/10 11:40:44 dsimcha One more alias this to re-enable.
(edit) @231 [231] 11/20/10 17:44:02 dsimcha Misc. small fixes: Bring back alias this and remove workarounds for bugs …
(edit) @230 [230] 11/16/10 20:49:02 dsimcha Misc small bugs and silliness exposed by testing on GDC.
(edit) @229 [229] 11/15/10 20:43:38 dsimcha More Linux fixes. I'm beginning to hate that OS.
(edit) @228 [228] 11/15/10 20:39:08 dsimcha More fixes for failing unit tests on Linux. I should really start running …
(edit) @227 [227] 11/15/10 20:31:38 dsimcha Fix some unit tests that fail in edge cases on Linux.
(edit) @226 [226] 11/13/10 18:58:27 dsimcha Fix 64-bit compilation errors. Code only passes semantic analysis, hasn't …
(edit) @225 [225] 10/26/10 19:37:36 dsimcha fix unittest.
(edit) @224 [224] 09/13/10 23:11:25 dsimcha Optimize the insertion sort base case a little.
(edit) @223 [223] 09/10/10 19:14:03 dsimcha Few small optimizations/bugfixes.
(edit) @222 [222] 09/10/10 09:12:13 dsimcha More small fixes.
(edit) @221 [221] 09/10/10 01:51:57 dsimcha S/b maxDiff.
(edit) @220 [220] 09/10/10 01:43:55 dsimcha Silly mistakes.
(edit) @219 [219] 09/10/10 01:30:27 dsimcha Mime stuff.
(edit) @218 [218] 09/10/10 01:29:42 dsimcha Add the files for real this time.
(edit) @217 [217] 09/10/10 01:27:58 dsimcha Add some basic support for PCA. It's still VERY experimental.
(edit) @216 [216] 09/09/10 20:37:16 dsimcha Residuals should copy input ROR to avoid unexpected side effects.
(edit) @215 [215] 09/09/10 20:31:47 dsimcha Some cheap little performance hacks.
(edit) @214 [214] 09/05/10 22:30:54 dsimcha Fixes for Appender-related bit rot.
(edit) @213 [213] 09/01/10 21:42:36 dsimcha Added fromDefaultKernel.
(edit) @212 [212] 08/22/10 21:53:46 dsimcha Docs.
(edit) @211 [211] 08/22/10 21:53:08 dsimcha Fix ranges: Add save() and @property stuff.
(edit) @210 [210] 08/22/10 21:23:24 dsimcha Docs.
(edit) @209 [209] 08/22/10 21:23:02 dsimcha Fix some style issues and a few 64 issues.
(edit) @208 [208] 08/12/10 23:14:03 dsimcha Use scope delegate.
(edit) @207 [207] 08/10/10 21:38:53 dsimcha Improve docs.
(edit) @206 [206] 08/10/10 21:22:14 dsimcha More optimization for KernelDensity?1D.
(edit) @205 [205] 08/10/10 00:33:34 dsimcha Speed up initialization of KernelDensity?1D ~200-fold.
(edit) @204 [204] 08/07/10 11:00:12 dsimcha Add better error handling.
(edit) @203 [203] 08/07/10 00:20:45 dsimcha Forgot const.
(edit) @202 [202] 08/07/10 00:19:17 dsimcha Docs.
(edit) @201 [201] 08/07/10 00:18:25 dsimcha N-D kernel density estimates.
(edit) @200 [200] 08/06/10 01:07:41 dsimcha Docs
(edit) @199 [199] 08/06/10 01:05:04 dsimcha More improvements to kerneldensity, add interquantileRange to support …
(edit) @198 [198] 08/05/10 18:40:50 dsimcha Remove obsolete reserve() function now that similar (and correct) function …
(edit) @197 [197] 08/05/10 18:23:37 dsimcha Fix bugs in kerneldensity.d. It really pays to eat your own dogfood.
(edit) @196 [196] 08/01/10 10:28:00 dsimcha Added cdf for kerneldensity.
(edit) @195 [195] 07/31/10 23:13:33 dsimcha kerneldensity should be in all.d
(edit) @194 [194] 07/31/10 23:09:32 dsimcha Add fromAlias.
Note: See TracRevisionLog for help on using the revision log.