AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Geometric Analysis of Matrix Sensing over Graphs

Haixiang Zhang, Ying Chen, Javad Lavaei

NeurIPS 2023 · Learning theory and algorithms › Matrix and tensor methods · approach: Randomized sketching for matrices · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace prior incoherence regularizer with a twice-differentiable convolution-smoothed regularizerregularized MSoG objective (12) · strict-saddle sampling-rate requirementrequired sampling rate np (bound): np >= Theta[mu^4 r^6 (kappa)^6 log n] -> np >= Theta[mu^2 r^3 (kappa)^2 log n]Improved
generalize RIP to partial observations (Omega-RIP) for losses on graph-observed entriesmatrix sensing over graphs · strict saddle propertyadmissible RIP constant delta: delta < 1/16Improved
raise Omega-RIP constant from 1/16 to 1/2 using loss f_{3/2}problem (12) · counterexample, any pspurious second-order critical point probability: probability at least (3 - sqrt5)/2 ~ 0.38Hurt
reduce Omega-RIP constant delta in the simulationperturbed accelerated gradient descent on f_c · n=10, r=5 synthetic, 100 instancessuccess rate (optimization complexity)Mixed
increase sampling rate p from 0.7 toward 1.0perturbed accelerated gradient descent on f_c · n=10, r=5 synthetic, 100 instancessuccess rate (optimization complexity)Mixed
use partial sampling (p<1) instead of full observation (p=1) when delta > 0.5perturbed accelerated gradient descent on f_c · n=10, r=5 syntheticsuccess rateImproved
vary delta below 1/2 versus vary pperturbed accelerated gradient descent on f_c · n=10, r=5 syntheticsuccess rateNo clear effect
gaussian linear measurements with m >= c n r / delta^2 on graph-restricted entrieslinear matrix sensing over graphs · Omega-RIP 2r,2rRIP holds w.h.p.: m >= cnr/delta^2Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy