← 研踪 PaperTrailarXiv:2610.36138 · v1
Symmetry Breaking Is the Price of Finite Capacity
首次提交 2026-10-27 02:45
版本更新 2026-10-27 02:45
雷达观测 2026-10-29 00:35
摘要
If rotating a problem never changes its answer, one might expect its best model to be rotation-invariant; we show that this fails, predictably and by an exact amount, when capacity is limited. A symmetry groups a model's directions into blocks of equally strong directions, a symmetric model must use each block whole, and when the budget cuts a block every optimal model breaks the symmetry. For a Gaussian problem with a $k$-unit bilinear predictor, the log-loss price of symmetry is exactly $(U_k-I_k)/(2σ^2)$, the signal of the best $k$ directions minus that of the best whole blocks. Because an attention head compares tokens through a similarity of rank at most its head dimension, whatever computation precedes it, the same price governs heads fitted to a symmetric similarity by squared error, and heads trained this way on three-dimensional directions break symmetry at exactly the predicted head dimensions, with the predicted rotation sensitivity (RMSE 0.004). Under softmax attention, flatter attention restores the predicted symmetric head where tested, while with peaked attention broken heads beat every whole-shell symmetric head at 16 of 20 head dimensions. We give a procedure that separates capacity-driven breaking from other causes.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-27 02:45 · 最新观测版本
Symmetry Breaking Is the Price of Finite Capacity
If rotating a problem never changes its answer, one might expect its best model to be rotation-invariant; we show that this fails, predictably and by an exact amount, when capacity is limited. A symmetry groups a model's directions into blocks of equally strong directions, a symmetric model must use each block whole, and when the budget cuts a block every optimal model breaks the symmetry. For a Gaussian problem with a $k$-unit bilinear predictor, the log-loss price of symmetry is exactly $(U_k-I_k)/(2σ^2)$, the signal of the best $k$ directions minus that of the best whole blocks. Because an attention head compares tokens through a similarity of rank at most its head dimension, whatever computation precedes it, the same price governs heads fitted to a symmetric similarity by squared error, and heads trained this way on three-dimensional directions break symmetry at exactly the predicted head dimensions, with the predicted rotation sensitivity (RMSE 0.004). Under softmax attention, flatter attention restores the predicted symmetric head where tested, while with peaked attention broken heads beat every whole-shell symmetric head at 16 of 20 head dimensions. We give a procedure that separates capacity-driven breaking from other causes.
查看此版本解读 →查看此版本原文 ↗