New DL algorithm detects critical chest X-ray findings without manual annotations.
problem Lack of explainability and manual annotation costs for DL models in medical imaging.
method Multi-instance learning approach to jointly classify and localize critical findings in CXR.
result Competitive classification results on three CXR datasets.
Single-timescale actor-critic finds globally optimal policy.
problem Finding globally optimal policy in reinforcement learning.
method Simultaneous actor and critic updates with linear or deep neural network approximations.
result Actor sequence converges to globally optimal policy at O(K−1/2) rate. Numerically locating the critical points of non-convex surfaces is a long-standing problem central to many fields. Recently, the loss surfaces of deep neural networks have been explored to gain insight into outstanding questions in optimization, generalization, and network architecture design. However, the degree to wh…
We find a resonance free region polynomially close to the critical line on Conformally compact manifolds with polyhomogeneous metric.
Paper finds critical metrics with pinched curvature are geodesic balls.
problem Identifying critical metrics with specific curvature constraints.
method Proved isometry to geodesic balls in S^n and provided conditions for the gradient of the potential function.
result Critical metrics with pinched curvature are isometric to geodesic balls in S^n.
The paper finds curves minimizing elastic energy pinned at endpoints.
problem Finding curves that minimize elastic energy with fixed endpoints.
method Applying the shooting method to identify and classify critical points.
result Critical points consist of wavelike elasticae, and minimizers have no loops or interior inflection points.
Gradient-based methods find saddle points, not critical points, in neural networks.
problem Gradient-based optimization methods converge to saddle points rather than critical points in deep neural networks.
method Critical point-finding methods used to analyze neural network losses.
result Gradient-based methods often converge to or pass through gradient-flat regions, where gradient norm has a stationary point.
Researchers extend Godbillon-Vey functional to almost contact manifolds, finding critical structures.
problem Finding optimal almost contact manifolds using the Godbillon-Vey functional.
method Introduced a Godbillon-Vey type functional for 3D almost contact manifolds and found its Euler-Lagrange equations.
result Constructed critical 3D almost contact manifolds with double-twisted product structure.
In this note I use cup-products and higher Massey products to find topological lower bounds on the number of geometrically distinct critical points of any closed 1-form in a given cohomology class.
Recent work in signal propagation theory has shown that dropout limits the depth to which information can propagate through a neural network. In this paper, we investigate the effect of initialisation on training speed and generalisation for ReLU networks within this depth limit. We ask the following research question:…
New findings on Chern flat metrics and their criticality.
problem Understanding critical Hermitian metrics on Chern flat manifolds.
method Analyzing Chern flat manifolds as compact quotients of complex Lie groups and studying their criticality.
result Chern flat metrics on semi-simple Lie groups are torsion-critical and vice versa.
We use numerical techniques to study the formation of singularities in Ricci flow. Comparing the Ricci flows corresponding to a one parameter family of initial geometries on S^3 with varying amounts of S^2 neck pinching, we find critical behavior at the threshold of singularity formation.
The year 2017 saw the rise and fall of the crypto-currency market, followed by high variability in the price of all crypto-currencies. In this work, we study the abrupt transition in crypto-currency residuals, which is associated with the critical transition (the phenomenon of critical slowing down) or the stochastic t…
We prove sharp pointwise decay estimates for critical Dirac equations on Rn with n≥2. They appear for instance in the study of critical Dirac equations on compact spin manifolds, describing blow-up profiles, and as effective equations in honeycomb structures. For the latter case, we find excited state…
Smaller actor-critic models lead to performance degradation and overfitting, highlighting the critic's role in value underestimation.
problem Performance degradation and overfitting in actor-critic models with smaller actors.
method Broad empirical investigations and analyses of asymmetric actor-critic setups, exploring techniques to mitigate value underestimation.
result Value underestimation is a key cause of performance degradation in smaller actor-critic models, and the critic plays a crucial role in mitigating this.
Study on Laplacian determinant in isosceles triangles, finding equilateral triangle minimizes determinant.
problem Finding the minimum of the spectral determinant on isosceles triangles.
method Analyzing the determinant of the Laplacian on Euclidean isosceles triangle envelopes of fixed area.
result Equilateral triangle envelope minimizes the determinant of the Laplacian.
Study finds critical points in perimeter functional for fixed volume sets.
problem Finding critical points in perimeter functional for sets of fixed volume.
method Utilizes Mazurwoski--Zhou techniques and new Cacciopoli set connectedness results.
result Constructs smooth almost embedded hypersurfaces with non-zero constant mean curvature.
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus o…
Accelerated method finds critical points faster on manifolds.
problem Optimization on non-convex manifolds.
method Accelerated gradient methods on Riemannian manifolds.
result Find approximate first-order critical points faster than regular gradient descent.
Empirical study on trends reversion in financial markets.
problem Understanding when trends in financial markets revert.
method Polynomial regression and bootstrapping on 30 years of daily futures prices.
result Trends revert when they reach a critical level of statistical significance.
New SGD algorithm finds critical points faster with second-order corrections.
problem Finding critical points in non-convex optimization efficiently.
method Uses Hessian-vector products to correct momentum bias in SGD.
result Finds ε-critical points in O(ε−3) time. Jakobson and Nadirashvili \cite{JN} constructed a sequence of eigenfunctions on T2 with a bounded number of critical points, answering in the negative the question raised by Yau \cite{Yau1} which asks that whether the number of the critical points of eigenfunctions for the Laplacian increases with the corresponding …
New method improves off-policy critic evaluation in reinforcement learning.
problem High variance and instability in off-policy policy evaluation.
method Doubly robust estimators applied to actor-critic algorithms.
result Doubly robust estimation significantly improves performance in continuous control tasks.
In this paper we produce a lower bound for the number of periodic orbits of certain Hamiltonian vector fields near Bott-nondegenerate symplectic critical submanifolds. This result is then related to the problem of finding closed orbits of the motion of a charged low energy particle on a Riemannian manifold under the in…
Gradient flow in phase retrieval escapes spurious minima with high probability.
problem Understanding gradient-based optimization in high-dimensional non-convex functions.
method Analytical and numerical study of gradient dynamics in phase retrieval.
result Gradient flow avoids spurious minima by drifting along unstable directions.
We study the feasibility and noise sensitivity of portfolio optimization under some downside risk measures (Value-at-Risk, Expected Shortfall, and semivariance) when they are estimated by fitting a parametric distribution on a finite sample of asset returns. We find that the existence of the optimum is a probabilistic …
We provide evidence that cumulative distributions of absolute normalized returns for the 100 American companies with the highest market capitalization, uncover a critical behavior for different time scales Δt. Such cumulative distributions, in accordance with a variety of complex --and financial-- systems, can be m…
New analysis shows actor-critic method converges efficiently in practical settings.
problem Understanding finite-time convergence of single-timescale actor-critic methods.
method Investigated online single-timescale actor-critic algorithm with linear function approximation and Markovian sampling.
result Proved convergence to ε-approximate stationary point with sample complexity of O(ε^(-2)).
This work analyzes actor-critic methods for faster convergence.
problem Finite-time analysis and sample complexity of two-time-scale actor-critic methods.
method Non-asymptotic analysis under non-i.i.d. setting, proving convergence to first-order stationary point.
result Actor-critic method finds a first-order stationary point with ildeO(ε−2.5) sample complexity. Current Deep Reinforcement Learning algorithms still heavily rely on handcrafted neural network architectures. We propose a novel approach to automatically find strong topologies for continuous control tasks while only adding a minor overhead in terms of interactions in the environment. To achieve this, we combine Neur…
New findings on mapping class group actions on the circle, improving critical regularity.
problem Improving understanding of mapping class group actions on the circle.
method Analyzing actions of non-solvable groups and finite index subgroups of mapping class groups.
result Critical regularity of mapping class groups is at most one for surfaces of complexity at least three.
In this paper, we present a probability one convergence proof, under suitable conditions, of a certain class of actor-critic algorithms for finding approximate solutions to entropy-regularized MDPs using the machinery of stochastic approximation. To obtain this overall result, we prove the convergence of policy evaluat…
The paper finds sign-changing solutions for a specific type of elliptic equation.
problem Existence of sign-changing solutions for a Yamabe type equation.
method Investigates a critical elliptic equation with a Yamabe type operator on a compact manifold with boundary.
result Existence of sign-changing solutions assured under certain geometric conditions.
We consider the problem of mean-variance portfolio optimization for a generic covariance matrix subject to the budget constraint and the constraint for the expected return, with the application of the replica method borrowed from the statistical physics of disordered systems. We find that the replica symmetry of the so…
Study finds non-uniqueness in sphere metrics with constant fractional curvature.
problem Non-uniqueness of metrics with constant positive fractional curvature on spheres.
method Bifurcation techniques applied to non-local equations with critical non-linearity.
result Non-uniqueness results for complete metrics on Sn∖Sk. The paper finds infinitely many magnetic geodesics on non-compact manifolds.
problem Existence and multiplicity of periodic orbits of magnetic flows.
method Morse theory applied to non-compact manifolds with energy levels above the Mañé critical value.
result Infinitely many noncontractible closed magnetic geodesics found.
Model criticism tool evaluates text coherence and structure in generated long-form text.
problem Evaluate the high-level structure of generated text for coherence, coreference, and topicality.
method Apply model criticism in latent space to compare real and generated data distributions.
result Transformer-based models struggle with maintaining structural coherence and coreference.
Grokking occurs in simple binary logistic classification near linear separability and noise.
problem Delayed generalization in binary logistic classification.
method Analytical and empirical insights into gradient descent dynamics near critical points.
result Logistic regression exhibits grokking when training data is nearly linearly separable from the origin with strong noise.
This work tackles risk-sensitive deep RL by optimizing policies with variance constraints.
problem Risk and aleatoric uncertainty in deep reinforcement learning.
method Lagrangian and Fenchel dualities to transform the problem into an unconstrained saddle-point policy optimization problem, and an actor-critic algorithm to iteratively update policy, Lagrange multiplier, and Fenchel dual variable.
result The proposed actor-critic algorithm finds a globally optimal policy at a sublinear rate.
Let M be a compact orientable irreducible 3-manifold and H be an unstabilized genus three Heegaard splitting of M. In this article, we will define a simplicial complex of weak reducing pairs for H and find several properties of this complex. Using this method, we will prove that an unstabilized Heegaard splitti…
Develops a method to simulate rare dangerous events in autonomous systems.
problem Rare dangerous events in safety-critical systems are hard to test in real-world settings.
method Combines exploration, exploitation, and optimization techniques for rare-event simulation.
result Provides rigorous guarantees for the performance of the method.
Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.
problem Inadequate policy imitation and limited transferable reward recovery in AIRL.
method Substituted built-in algorithm with SAC for policy updating and proposed PPO-AIRL + SAC hybrid framework.
result SAC improves policy imitation but hinders reward recovery; PPO-AIRL + SAC achieves satisfactory transfer effect.
The study finds the minimum number of critical points for functionals on Frechet spaces and Finsler manifolds.
problem Finding the minimum number of critical points for functionals on Frechet spaces and Finsler manifolds.
method Applying the Lusternik-Schnirelmann category to evaluate the minimal number of critical points for Keller Cc1-functionals on Frechet spaces and Finsler manifolds. result The minimal number of critical points is determined by the Lusternik-Schnirelmann category.
Riemannian gradient descent escapes some spurious critical points on low-rank matrix manifold.
problem Spurious critical points on the boundary of low-rank matrix manifold.
method Riemannian gradient descent with dynamical low-rank approximation and rescaled gradient flow.
result Riemannian gradient descent escapes some spurious critical points on the boundary of the manifold.
Study shows flash crashes in finance are self-organized criticality events.
problem Understanding and predicting anomalous price events in high-frequency finance.
method Investigated volume distributions during flash crashes and linked them to self-organized criticality.
result Volume distributions during flash crashes indicate a diverging second moment, suggesting self-organized criticality.
New critics improve VAEs by preventing latent collapse.
problem Posterior collapse in VAEs where latent variables are ignored.
method Inference critics that detect and incentivize meaningful latent representations.
result Optimizing inference critics increases mutual information between latent and observations.
Study estimates personalized effects of maternal PM2.5 exposure on birth weight.
problem Identify critical windows and heterogeneity in maternal PM2.5 exposure effects on birth weight.
method Heterogeneous Distributed Lag Models and Bayesian Additive Regression Trees.
result Evidence of heterogeneity in PM2.5-birth weight relationship, with some dyads showing 3x larger decrease.
We examine the total mixed scalar curvature of a fixed distribution as a functional of a pseudo-Riemannian metric. We develop variational formulas for quantities of extrinsic geometry of the distribution to find the critical points of this action. Together with the arbitrary variations of the metric, we consider also v…