713 Commits

Author SHA1 Message Date
Daniel Povey
a9edecd32c Conformed that symmetrizing helps because of interaction with regular update; still meta_lr_scale=0 best :-( 2022-07-09 05:20:04 +08:00
Daniel Povey
52bfb2b018 This works better for reasons I dont understand. transpose is enough, same as symmetrizing. 2022-07-08 11:53:59 +08:00
Daniel Povey
e9ab1ddd39 Inconseqeuential config change 2022-07-08 11:03:16 +08:00
Daniel Povey
be6680e3ba Couple configuration changes, comment simplification 2022-07-08 09:46:42 +08:00
Daniel Povey
75e872ea57 Fix bug in getting denom in proj update 2022-07-08 09:13:54 +08:00
Daniel Povey
914ac1e621 Works better with meta_lr_scale=0, must be bug. 2022-07-08 09:07:06 +08:00
Daniel Povey
923468b8af Deal with SVD failure better. 2022-07-08 09:00:12 +08:00
Daniel Povey
97feb8a3ec Reduce meta_lr_scale, reduces loss @140 from 1.4 to 0.39 2022-07-08 06:33:07 +08:00
Daniel Povey
b6199a71e9 Introduce delta_scale to slow down changes on M; significantly better. 2022-07-08 06:05:31 +08:00
Daniel Povey
ceb9815f2b Increase lr_est_period 2022-07-08 05:51:18 +08:00
Daniel Povey
fb36712e6b Another bug fix, regarding Q being transposed. 2022-07-08 05:22:24 +08:00
Daniel Povey
ad2e698fc3 Cleanups 2022-07-08 04:44:21 +08:00
Daniel Povey
04d2e10b4f Version that runs 2022-07-08 04:37:46 +08:00
Daniel Povey
e6d00ee3e4 More drafts of new method, not tested. 2022-07-06 23:05:06 -07:00
Daniel Povey
26815d177f Draft of the new method.. 2022-07-06 22:59:36 -07:00
Daniel Povey
e9e2a85c95 In the middle of reworking for new idea 2022-07-06 13:35:19 -07:00
Daniel Povey
41368f6b63 Change comment 2022-07-05 17:11:45 -07:00
Daniel Povey
2692d5f903 Closer to finished 2022-06-30 23:54:26 -07:00
Daniel Povey
d64cb1cb48 draft, not working, will edit locally 2022-06-30 15:35:26 +08:00
Daniel Povey
0b811546f3 Apply reverse_cutoff with param_pow, to make it not too strong. 2022-06-26 11:07:08 +08:00
Daniel Povey
0aa5a334d6 Fix regarding reverse_cutoff formula 2022-06-25 18:24:05 +08:00
Daniel Povey
8a0277d493 Increase param_reverse_cutoff from 4 to 16 2022-06-25 18:02:00 +08:00
Daniel Povey
2ccc7ccbeb Make the application of param_reverse_cutoff conditional, not applied when rank is a problem 2022-06-25 17:56:04 +08:00
Daniel Povey
146d7c5a93 Bug fix 2022-06-24 19:49:13 +08:00
Daniel Povey
117d348f70 This time get it right, last time was starting from wrong base. 2022-06-24 19:00:58 +08:00
Daniel Povey
6002e19836 Change max_fullcov_size back to 1023.. doing it this way because I forgot to commit the changes on this branch 2022-06-24 18:59:34 +08:00
Daniel Povey
c2ec901e73 Change param_pow from 0.75 to 0.5 2022-06-24 17:14:41 +08:00
Daniel Povey
f327407308 Avoid error if svd fails 2022-06-24 13:20:20 +08:00
Daniel Povey
2233c852fd Increase max_fullcov_size from 1023 to 2048 2022-06-24 13:02:17 +08:00
Daniel Povey
683b8e1504 Some code reworking and fixes, rationalizing how speedup is done and fix an issue affecting learning rate. 2022-06-23 15:40:51 +08:00
Daniel Povey
c34344e98f Change param_pow,grad_pow to 0.75,0.95 2022-06-23 14:04:11 +08:00
Daniel Povey
3767f3d616 Reducd param_pow from 0.8 to 0.7 2022-06-23 11:12:12 +08:00
Daniel Povey
ca17f23da3 Reduce powers to 0.8,0.85 2022-06-23 11:09:27 +08:00
Daniel Povey
09282ca28c Reduce some print statements, convert some to info 2022-06-23 10:41:08 +08:00
Daniel Povey
7f756b2910 Introduce grad_pow option, set it to 0.9 and param_pow to 0.85 2022-06-23 10:33:14 +08:00
Daniel Povey
4124cd7241 Reduce debug frequencies 2022-06-20 13:48:42 +08:00
Daniel Povey
c10a9889fa Reduce grad_eps to 1e-14 2022-06-20 13:45:53 +08:00
Daniel Povey
b560221eea Change param_pow to 0.75 2022-06-20 00:29:07 +08:00
Daniel Povey
cf816a9138 Change param_pow to 0.0 2022-06-19 22:44:17 +08:00
Daniel Povey
ad5337fe95 Set param_pow to 0.5 2022-06-19 22:14:34 +08:00
Daniel Povey
8acc398428 Reduce debug freq 2022-06-19 11:21:48 +08:00
Daniel Povey
29dfe37f22 Implement min,max param rms 2022-06-18 22:22:23 +08:00
Daniel Povey
3fb3cc4e23 Make random cov have correct diagonal; reset grad_min_rand to 0. 2022-06-18 17:04:44 +08:00
Daniel Povey
3f0b57403e Min-rand-scale 0.2 for grad cov 2022-06-18 16:26:37 +08:00
Daniel Povey
e996f7f371 First version I am running, of the speedup code 2022-06-18 15:17:51 +08:00
Daniel Povey
a6bf32c3e0 Fast code seems to pass tests. 2022-06-18 12:56:16 +08:00
Daniel Povey
ea5cd69e3b Possibly fix bug RE learning rate 2022-06-17 20:50:00 +08:00
Daniel Povey
cbccc1dd91 Fix bias_correction2, power of 0.5 2022-06-17 20:20:16 +08:00
Daniel Povey
2d13b682fe Revert param_rel_eps to old value 2022-06-17 18:22:27 +08:00
Daniel Povey
92fb1c52c8 Reduce debug statement frequency 2022-06-17 16:03:50 +08:00