55 Commits

Author SHA1 Message Date
Marcel Keller
bf7f8f4b65 Expected communication cost in compiler. 2025-12-24 13:47:42 +11:00
Marcel Keller
a2ab47642b Fix regression. 2025-11-07 15:07:54 +11:00
Hidde L
bfe3e7e038 Make interface of Dropout backwards compatible 2025-11-06 16:16:21 -05:00
Hidde L
e17e175b16 Merge FlexDropout into Dropout
Update mnist_full examples using Dropout
Clean up code style
2025-10-21 16:26:15 +02:00
Hidde L
ba2b440712 Merge FlexDense with Dense 2025-10-21 15:55:20 +02:00
Hidde L
9ac22e3650 fix flexdense 2025-10-21 15:45:07 +02:00
Hidde L
2162b79b73 Revert unrelated changes 2025-10-20 11:14:38 +02:00
Hidde L
d0f955c2d3 avg diff, dropout 2025-10-14 21:43:18 +02:00
Hidde L
f8139db805 Add BERT layers and test script 2025-10-14 19:58:44 +02:00
Marcel Keller
99c63a6fbe Sample masking in linear regression. 2025-09-12 17:00:30 +08:00
Marcel Keller
b52d0ac5da Sample masking in logistic regression. 2025-09-11 17:01:44 +08:00
Marcel Keller
9f2a641a94 Protocols with function-dependent preprocessing. 2025-05-30 13:35:02 +10:00
Wenqiang Ruan
1b3b18870f Fix a bug when using multithreading 2024-12-05 14:32:15 +08:00
wqruan
551e23c720 a small improvement on SGD with mementum optimizer 2024-12-02 11:12:29 +08:00
wqruan
7900ef8b0a a small improvement on SGD with mementum optimizer 2024-12-02 11:05:02 +08:00
Marcel Keller
91321ff8cd Functionality to call high-level code from C++. 2024-11-21 13:14:54 +11:00
Marcel Keller
533372a8cb Allocate trainable parameters in benchmark runs. 2024-09-18 13:14:58 +10:00
Marcel Keller
b6aa32f26d More PyTorch functionality. 2024-08-12 22:27:45 +10:00
Marcel Keller
78fe3d8bad Maintenance. 2024-07-09 12:19:52 +10:00
Parker Diamond
10484c08e3 Calculate output shape in accordance to PyTorch docs 2024-05-20 15:50:45 -04:00
Marcel Keller
f86ce7c0b8 Fix bug with large batch sizes. 2024-04-22 16:17:58 +10:00
Marcel Keller
0468abb5f6 Missing batch normalization functionality. 2024-04-19 13:16:06 +10:00
Marcel Keller
cf4426fdb3 Multinode computation. 2023-12-14 12:17:54 +11:00
Marcel Keller
2813c0ef0f Maintenance. 2023-08-14 18:29:46 +10:00
Marcel Keller
17f683c9ab Conversion of PyTorch regression models with multiple targets. 2023-06-02 20:49:11 +10:00
Marcel Keller
6cc3fccef0 Maintenance. 2023-05-09 14:50:53 +10:00
Marcel Keller
95ea9f3cc7 Fix bug in square layer back-propagation. 2023-03-29 10:41:05 +11:00
Marcel Keller
5153c63d2f More accessible machine learning functionality. 2023-02-16 12:35:18 +11:00
Marcel Keller
a3acf6e8a3 Fix bugs in MaxPool. 2023-01-04 16:30:22 +11:00
Marcel Keller
cd25c2e9f1 Decision tree training. 2022-11-09 11:22:18 +11:00
Marcel Keller
6a424539c9 SoftSpokenOT. 2022-08-25 13:23:18 +10:00
Marcel Keller
9ef15cc2f5 Protocol in dealer model. 2022-04-19 15:13:19 +02:00
Marcel Keller
0f7020d791 Semi-honest computation based on threshold semi-homomorphic encryption. 2022-02-17 13:24:52 +11:00
jvmncs
9fcffad831 approx_sigmoid is attributed to an earlier paper 2022-01-18 08:49:00 -05:00
Marcel Keller
e07d9bf2a3 Maintenance. 2022-01-11 16:05:26 +11:00
Marcel Keller
40431cd52a Fix bug in early abort. 2021-11-25 11:24:51 +11:00
Marcel Keller
32950fe8d4 Maintenance. 2021-11-04 16:24:34 +11:00
Marcel Keller
799929b801 Optimized matrix multiplication in Hemi. 2021-09-17 14:31:25 +10:00
Marcel Keller
c597554af9 ATLAS. 2021-08-06 18:25:27 +10:00
Marcel Keller
a94c2d7613 Missing code for square activation. 2021-07-09 20:21:26 +10:00
Marcel Keller
96a21a1506 Bug in machine learning inference. 2021-07-02 20:44:31 +10:00
Marcel Keller
99c0549e72 Convolutional neural network training. 2021-07-02 15:50:34 +10:00
Marcel Keller
0f656fa7b7 ARM support. 2021-04-19 21:28:22 +10:00
Marcel Keller
c9b03d8b51 Distributed key generation for homomorphic encryption with active security. 2021-02-23 17:41:35 +11:00
Marcel Keller
cdb8d6f337 Various improvements. 2020-12-11 16:24:28 +11:00
Marcel Keller
f42e614399 Rep4, SPDZ-wise, MNIST training. 2020-10-28 11:21:54 +11:00
Marcel Keller
ad583afb7e Various improvements. 2020-08-24 23:29:03 +10:00
Marcel Keller
3f9f3be575 Half-gate garbling, native 2D convolution, TensorFlow inference. 2020-06-15 15:23:05 +10:00
Marcel Keller
4ef6b6d873 Maintenance. 2020-05-08 21:43:05 +10:00
Marcel Keller
24926df83b Bristol Fashion. 2020-04-02 09:09:45 +02:00