Gahow Wang
f22429f5b8
New xtrain-optim crate. AdamW with per-param m/v moments keyed by params() index, global bias correction, and decoupled weight decay (matches torch.optim.AdamW). Split into a pure-host step_host (flat f32 buffers, unit-testable on a GPU-less host) and a step(&[Var]) wrapper that round-trips each param value/grad through the GPU tensor (gated not(no_cuda)). Per-step lr argument leaves room for an LR schedule. Host unit test checks the update against an independent reference recurrence over 20 steps and the pure-decay (g=0) boundary. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
13 lines
318 B
TOML
13 lines
318 B
TOML
[package]
|
|
name = "xtrain-optim"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
|
|
[dependencies]
|
|
xtrain-tensor = { path = "../xtrain-tensor" }
|
|
xtrain-autodiff = { path = "../xtrain-autodiff" }
|
|
|
|
[dev-dependencies]
|
|
# Acceptance tests drive the GPU (device selection) directly.
|
|
xtrain-cuda = { path = "../xtrain-cuda" }
|