Functional renormalization group and the field theory of disordered elastic systems.

We study elastic systems, such as interfaces or lattices, pinned by quenched disorder. To escape triviality as a result of "dimensional reduction," we use the functional renormalization group. Difficulties arise in the calculation of the renormalization group functions beyond one-loop order. Even worse, observables such as the two-point correlation function exhibit the same problem already at one-loop order. These difficulties are due to the nonanalyticity of the renormalized disorder correlator at zero temperature, which is inherent to the physics beyond the Larkin length, characterized by many metastable states. As a result, two-loop diagrams, which involve derivatives of the disorder correlator at the nonanalytic point, are naively "ambiguous." We examine several routes out of this dilemma, which lead to a unique renormalizable field theory at two-loop order. It is also the only theory consistent with the potentiality of the problem. The beta function differs from previous work and the one at depinning by novel "anomalous terms." For interfaces and random-bond disorder we find a roughness exponent zeta=0.208 298 04epsilon+0.006 858epsilon(2), epsilon=4-d. For random-field disorder we find zeta=epsilon/3 and compute universal amplitudes to order O(epsilon(2)). For periodic systems we evaluate the universal amplitude of the two-point function. We also clarify the dependence of universal amplitudes on the boundary conditions at large scale. All predictions are in good agreement with numerical and exact results and are an improvement over one loop. Finally we calculate higher correlation functions, which turn out to be equivalent to those at depinning to leading order in epsilon.