← Research
ICML 2026

DP-KFC: data-free preconditioning for privacy-preserving deep learning

Deep networks have highly anisotropic loss landscapes; DP-SGD injects isotropic noise. Fixing that mismatch usually costs private data or public data. It turns out the geometry was never in the data — it's in the architecture.

Venue · ICML 2026 Area · Private optimisation · KFAC At · CERN Download PDF ↓

The geometric mismatch

DP-SGD earns its guarantee with two spherical operations: clip every per-sample gradient to a global ℓ₂ ball, then add isotropic Gaussian noise. But loss landscapes are anything but spherical — curvature varies by orders of magnitude across parameter directions. The result is an isotropy mismatch: low-sensitivity directions drown in noise while high-sensitivity ones are over-clipped, producing wildly heterogeneous signal-to-noise ratios across layers. In a transformer trained with standard DP-SGD, some layers' signal simply collapses.

Why the standard escapes fail

The classical answer is preconditioning: rescale updates by curvature. In a private setting, both ways of estimating that curvature are compromised:

The insight

The Fisher Information Matrix decouples into architectural sensitivity — recoverable by probing the network with synthetic noise — and input correlations — approximable from modality-level frequency statistics. Neither component needs the private data. Mean-field theory makes this precise: the trace of each layer's Fisher block is governed by depth, width, initialisation, and nonlinearity — properties of the architecture, not the dataset.

The method

DP-KFC constructs KFAC preconditioners by probing the network with structured synthetic inputs that carry no privacy cost. For images, that structure is pink noise: natural images universally follow a 1/f power spectrum, so colored noise with the same spectral decay reproduces the local and global correlations a convolution or attention layer actually sees. For text, structured random token sequences play the same role. Labels are sampled uniformly at random — KFAC's factors depend on error magnitudes, not label correctness.

A forward and backward pass over the synthetic batch yields per-layer Kronecker factors; eigendecomposition and damping give the inverse-square-root preconditioner. Applied to gradients before clipping and noising — the scale-then-privatise principle — it makes the private update approximately isotropic, so DP-SGD's spherical clipping and spherical noise finally match the geometry they operate in. The privacy analysis is untouched: nothing in the preconditioner ever saw the data.

Results

In strong privacy regimes (ε ≤ 3), DP-KFC consistently outperforms DP-SGD and adaptive baselines across modalities — CNNs and transformers, vision and text. Layer-wise SNR profiles show it matching the geometry of data-dependent preconditioners without touching any external data. And it matches private-data preconditioners while public-data proxies degrade by up to 4.8% under domain mismatch — the curvature really can be estimated without spending budget or importing distribution shift.

That last comparison is the practical point: in regulated domains like medical imaging, where public proxies don't exist and every ε counts, data-free is not a convenience — it is the only preconditioning that doesn't undermine the guarantee it serves. A companion line of work (MICCAI 2026, under review) pushes the same architecture-driven principle into sample-efficient differentially private medical image segmentation.

← Synthetic data The Missing Sampler →