From cd99d6b874d9d09b3bb87b8485cc787885af71f1 Mon Sep 17 00:00:00 2001
From: YurenHao0426 <blackhao0426@gmail.com>
Date: Tue, 13 Jan 2026 23:49:05 -0600
Subject: init commit

---
 scripts/run_stable_init.sbatch | 60 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 60 insertions(+)
 create mode 100644 scripts/run_stable_init.sbatch

(limited to 'scripts/run_stable_init.sbatch')

diff --git a/scripts/run_stable_init.sbatch b/scripts/run_stable_init.sbatch
new file mode 100644
index 0000000..eefe6bb
--- /dev/null
+++ b/scripts/run_stable_init.sbatch
@@ -0,0 +1,60 @@
+#!/bin/bash
+#SBATCH --job-name=snn_stable
+#SBATCH --account=bfqt-delta-gpu
+#SBATCH --partition=gpuA40x4
+#SBATCH --nodes=1
+#SBATCH --ntasks=1
+#SBATCH --cpus-per-task=8
+#SBATCH --gpus-per-node=1
+#SBATCH --mem=64G
+#SBATCH --time=48:00:00
+#SBATCH --output=runs/slurm_logs/%j_stable_init.out
+#SBATCH --error=runs/slurm_logs/%j_stable_init.err
+
+# ============================================================
+# Experiment 3: Stability-Aware Initialization
+# ============================================================
+# Hypothesis: The network starts chaotic (lambda~2-3) because of
+# standard Kaiming initialization. Using smaller weights from the
+# start should produce more stable dynamics.
+#
+# Stable init strategy:
+# - Scale down weights by 0.5
+# - Use orthogonal init for linear layers (preserves gradient norm)
+# - Should produce lambda closer to 0 initially
+# ============================================================
+
+set -e
+
+PROJECT_DIR="/projects/bfqt/users/yurenh2/ml-projects/snn-training"
+cd "$PROJECT_DIR"
+
+mkdir -p runs/slurm_logs data
+
+echo "============================================================"
+echo "STABLE INITIALIZATION Experiment"
+echo "Job ID: $SLURM_JOB_ID | Node: $SLURM_NODELIST"
+echo "Start: $(date)"
+echo "============================================================"
+nvidia-smi --query-gpu=name,memory.total --format=csv,noheader
+echo "============================================================"
+
+python files/experiments/depth_scaling_benchmark.py \
+    --dataset cifar100 \
+    --depths 4 8 12 16 \
+    --T 4 \
+    --epochs 150 \
+    --batch_size 128 \
+    --lr 0.001 \
+    --lambda_reg 0.1 \
+    --lambda_target -0.1 \
+    --reg_type squared \
+    --warmup_epochs 20 \
+    --stable_init \
+    --data_dir ./data \
+    --out_dir runs/depth_scaling_stable_init \
+    --device cuda
+
+echo "============================================================"
+echo "Finished: $(date)"
+echo "============================================================"
-- 
cgit v1.2.3