[KongchangAI]
Conceptlinear bound propagation

Linear Bound Propagation

A classical class of network verification methods that processes a network operation by operation to propagate linear bounds. At second-order terms it pays the sum of the per-operation maxima rather than the coupled maximum, which results in a loss of tightness in the derived bounds.

Timeline (last 90 days)

Nov 10

GEAR is a GPU-accelerated global nonlinear programming (NLP) solver whose core idea originates from the linear bound propagation framework in neural network verification.

Unverified50%
Nov 10

GEAR uses linear bound propagation as a relaxation means for nonlinear constraints, provides lower bounds for branch and bound, and performs safe pruning when a subregion is detected to be infeasible.

Unverified50%
Nov 10

Linear bound propagation is a core technique in the formal verification of neural networks, used to compute safety bounds on neural network outputs with respect to input perturbations.

Unverified50%
Nov 10

The linear bound propagation framework has been widely applied in verification tools such as ERAN and CROWN.

Unverified50%
Nov 3

On GPT-2, the moment relaxation certificate is tighter than linear bound propagation on every attention head.

Unverified50%
Nov 3

The looseness of linear bound propagation exactly matches the theoretically predicted per-operation excess.

Unverified50%
Nov 3

Per-operation relaxation (including linear bound propagation) computes, at the second-order term, the sum of the maxima of each operation rather than a coupled maximum, resulting in a loss of tightness.

Unverified50%

All Facts (7)

Source Articles