167 Commits

Author	SHA1	Message	Date
Daniel Povey	cb67540cdc	this version not working great	2022-07-30 21:14:03 -07:00
Daniel Povey	790e8c4ba9	Changes that should not really affect the results, just cleanup.	2022-07-30 19:20:36 -07:00
Daniel Povey	5184ac570d	Removing phase1, adding regular smoothing with the mean.	2022-07-30 19:15:51 -07:00
Daniel Povey	105d49d31b	Big simplification to update rule	2022-07-30 00:21:12 -07:00
Daniel Povey	4d5323d6a3	Change cov_min to intermediate value, not seeing clear diffs from changing it	2022-07-30 09:06:23 +08:00
Daniel Povey	c0e652ea87	Fix code, was smoothing in wrong basis.	2022-07-30 09:01:11 +08:00
Daniel Povey	17bc002e6e	Refactoring that does not affect results.	2022-07-30 07:45:29 +08:00
Daniel Povey	3110138ab5	Smooth grad_cov with eps; add a 4th stage of smoothing, this time on Z_inv.	2022-07-30 07:30:32 +08:00
Daniel Povey	3ad042444e	More changes to reduce numerical roundoff for dims with zero grad and params.	2022-07-29 14:38:50 +08:00
Daniel Povey	3c1fddaf48	Rework computation to reduce numerical roundoff	2022-07-29 06:22:17 +08:00
Daniel Povey	0d038a6ea4	Remove debugging statement	2022-07-28 09:26:11 +08:00
Daniel Povey	8654a7385d	Add denom_rel_eps, and set it to 1e-05	2022-07-28 09:10:20 +08:00
Daniel Povey	dc565f729b	Take into account various outcomes from parameter tuning	2022-07-28 09:06:59 +08:00
Daniel Povey	fe595f8772	Improve debugging output.	2022-07-25 09:02:36 +08:00
Daniel Povey	854c2965a9	Fix bug regarding G_prime being zero	2022-07-25 06:57:52 +08:00
Daniel Povey	3acdf3b395	Reworking the computation of Z to be numerically better.	2022-07-25 06:37:26 +08:00
Daniel Povey	5513f7fee5	Initial version of fixing numerical issue, will continue though	2022-07-25 06:27:01 +08:00
Daniel Povey	06718052ec	Refactoring, putting tunable values in constructor, a little cleanup	2022-07-25 04:31:42 +08:00
Daniel Povey	8efc512823	Remove some debugging code, found the mismatch	2022-07-24 11:52:10 +08:00
Daniel Povey	ba96439c76	Saving version I am trying to debug	2022-07-24 11:00:40 +08:00
Daniel Povey	962e95f119	Using a more flexible test. Moved to simpler update , tuned diffrently.	2022-07-24 09:20:53 +08:00
Daniel Povey	b8a9485011	Print git version for test output	2022-07-24 06:54:29 +08:00
Daniel Povey	48ac7e0bc3	Add max as well as min to G_prime	2022-07-24 06:50:05 +08:00
Daniel Povey	6290fcb535	Cleanup and refactoring	2022-07-24 05:48:38 +08:00
Daniel Povey	8a9bbb93bc	Cosmetic fixes	2022-07-24 04:45:57 +08:00
Daniel Povey	966ac36cde	Fixes to comments	2022-07-24 04:36:41 +08:00
Daniel Povey	33ffd17515	Some cleanup	2022-07-24 04:22:11 +08:00
Daniel Povey	ddceb7963b	Interpolate between iterative estimate of scale, and original value.	2022-07-23 15:27:48 +08:00
Daniel Povey	2c4bdd0ad0	Add _update_param_scales_simple(), add documentation	2022-07-23 14:49:58 +08:00
Daniel Povey	9730352257	Redce smoothing constant slightly	2022-07-23 13:12:31 +08:00
Daniel Povey	e1873fc0bb	Tune phase2 again, from 0.005,5.0 to 0.01,40. Epoch 140 is 0.21/0.149	2022-07-23 10:10:01 +08:00
Daniel Povey	0fc58bac56	More tuning, epoch-140 results are 0.23,0.11	2022-07-23 09:52:51 +08:00
Daniel Povey	34a2d331bf	Smooth in opposite orientation to G	2022-07-23 09:38:16 +08:00
Daniel Povey	a972655a70	Tuning.	2022-07-23 09:15:49 +08:00
Daniel Povey	b47433b77a	Fix bug in smooth_cov, for power==1.0	2022-07-23 09:06:03 +08:00
Daniel Povey	cc388675a9	Bug fix RE rankj	2022-07-23 08:24:59 +08:00
Daniel Povey	dee496145d	this version performs way worse but has bugs fixed, can optimize from here.	2022-07-23 08:11:20 +08:00
Daniel Povey	dd10eb140f	First version after refactorization and changing the math, where optim.py runs	2022-07-23 06:32:56 +08:00
Daniel Povey	4da4e69fba	Draft of new way of smoothing param_rms, diagonalized by grad	2022-07-22 06:37:20 +08:00
Daniel Povey	a63afe348a	Increase max_lr_factor from 3.0 to 4.0	2022-07-19 06:56:41 +08:00
Daniel Povey	79a2f09f62	Change how formula for max_lr_factor works, and increase factor from 2.5 to 3.	2022-07-19 06:54:49 +08:00
Daniel Povey	525c097130	Increase power from 0.7 to 0.75	2022-07-19 05:44:03 +08:00
Daniel Povey	2dff1161b4	Reduce max_lr_factor from 3.0 to 2.5	2022-07-19 05:15:03 +08:00
Daniel Povey	8bb44b2944	Change param_pow from 0.6 to 0.7	2022-07-19 05:08:32 +08:00
Daniel Povey	bb1e1e154a	Increasing param_pow to 0.6 and decreasing max_lr_factor from 4 to 3.	2022-07-18 09:06:32 +08:00
Daniel Povey	8db3b48edb	Update parameter dependent part of cov more slowly, plus bug fix.	2022-07-18 05:26:55 +08:00
Daniel Povey	198cf2635c	Reduce param_pow from 0.5 to 0.4.	2022-07-17 15:35:07 +08:00
Daniel Povey	3857a87b47	Merge branch 'merge_refactor_param_cov_norank1_iter_batch_max4.0_pow0.5_fix2r_lrupdate200_2k_ns' into merge2_refactor_max4.0_pow0.5_200_1k_ma3.0	2022-07-17 15:32:43 +08:00
Daniel Povey	a572eb4e33	Reducing final lr_update_period from 2k to 1k	2022-07-17 12:56:02 +08:00
Daniel Povey	7e88e2a0e9	Increase debug freq; add type to diagnostics and increase precision of mean,rms	2022-07-17 06:40:16 +08:00