19 citations · 32 across the 13 of their papers we have counts for
13 papers
PROMA: Projected Microbatch Accumulation for Reference-Free Proximal Policy Updates
Nilin Abrahamsen
This note introduces Projected Microbatch Accumulation (PROMA), a reference-free proximal policy method that controls KL divergence by projecting away high-variance components of t…
ISOPO: Proximal policy gradients without pi-old
Nilin Abrahamsen
This note introduces Isometric Policy Optimization (ISOPO), an efficient method to approximate the natural policy gradient in a single gradient step. In comparison, existing proxim…
A Kaczmarz-inspired approach to accelerate the optimization of neural network wavefunctions
Gil Goldshlager, Nilin Abrahamsen, Lin Lin
Neural network wavefunctions optimized using the variational Monte Carlo method have been shown to produce highly accurate results for the electronic structure of atoms and small m…
Inventing art styles with no artistic training data
Nilin Abrahamsen, Jiahao Yao
We propose two procedures to create painting styles using models trained only on natural images, providing objective proof that the model is not plagiarizing human art styles. In t…
Anti-symmetric Barron functions and their approximation with sums of determinants
Nilin Abrahamsen, Lin Lin
A fundamental problem in quantum physics is to encode functions that are completely anti-symmetric under permutations of identical particles. The Barron space consists of high-dime…
Convergence of variational Monte Carlo simulation and scale-invariant pre-training
Nilin Abrahamsen, Zhiyan Ding, Gil Goldshlager +1
We provide theoretical convergence bounds for the variational Monte Carlo (VMC) method as applied to optimize neural network wave functions for the electronic structure problem. We…
Efficient anti-symmetrization of a neural network layer by taming the sign problem
Nilin Abrahamsen, Lin Lin
Explicit antisymmetrization of a neural network is a potential candidate for a universal function approximator for generic antisymmetric functions, which are ubiquitous in quantum…
Entanglement area law for 1D gauge theories and bosonic systems
Nilin Abrahamsen, Yu Tong, Ning Bao +2
We prove an entanglement area law for a class of 1D quantum systems involving infinite-dimensional local Hilbert spaces. This class of quantum systems include bosonic models such a…
Short proof of a spectral Chernoff bound for local Hamiltonians
Nilin Abrahamsen
We give a simple proof of a Chernoff bound for the spectrum of a -local Hamiltonian based on Weyl's inequalities. The complexity of estimating the spectrum's -th quantile…
Solving degenerate 2D frustration-free spin systems in sub-exponential time
Nilin Abrahamsen
We give an improved analysis of approximate ground space projectors (AGSPs) to obtain a sharp error reduction bound in the setting a degenerate ground space. The improved tools imp…
Sharp implications of AGSPs for degenerate ground spaces
Nilin Abrahamsen
We generalize the `off-the-rack' AGSPentanglement bound implication of [Arad, Landau, and Vazirani '12] from unique ground states to degenerate ground spaces. Our cond…
A polynomial-time algorithm for ground states of spin trees
Nilin Abrahamsen
We prove that the ground states of a local Hamiltonian satisfy an area law and can be computed in polynomial time when the interaction graph is a tree with discrete fractal dimensi…
Sparse Gaussian ICA
Nilin Abrahamsen, Philippe Rigollet
Independent component analysis (ICA) is a cornerstone of modern data analysis. Its goal is to recover a latent random vector S with independent components from samples of X=AS wher…