New method for inferring time series graph from sparse-group log-sum penalty.
problem Inferring conditional independence graph from high-dimensional stationary multivariate Gaussian time series.
method Sparse-group log-sum penalty (LSP) and alternating direction method of multipliers (ADMM) for iterative optimization.
result Local convergence of inverse PSD estimators to the true value with rate of convergence.
Two new methods improve block-sparse signal recovery from noisy data.
problem Recovering block-sparse signals with unknown partitions.
method LogLOP-l2/l1 and AdaLOP-l2/l1 methods using log-sum penalty and MCP.
result Our methods outperform existing techniques in estimation accuracy.
Proposes a differentiable LSE-ICNN for modeling multi-well potentials.
problem Modeling multi-well potentials in various scientific domains.
method Log-sum-exponential (LSE) mixture of input convex neural network (ICNN) modes.
result Smooth surrogate that retains convexity within basins and allows gradient-based learning.
Novel LSE estimator improves off-policy learning and evaluation.
problem High variance and poor performance with low-quality propensity scores and heavy-tailed reward distributions.
method Introduces a novel estimator based on the log-sum-exponential (LSE) operator.
result Achieves convergence rate of O(n−ε/(1+ε)) for regret bounds. Unified analysis of multi-attribute graph learning with non-convex penalties.
problem Graph inference from multi-attribute data.
method Penalized log-likelihood objective function with ADMM and local linear approximation.
result Local consistency in support recovery and precision matrix estimation for non-convex penalties.
Gradient descent on LSE objectives implicitly performs EM, leading to collapse without volume control.
problem Gradient collapse in autoencoders without volume control.
method Introduced a single-layer encoder with an LSE objective and InfoMax regularization for volume control.
result Gradient--responsibility identity holds exactly; LSE alone collapses; variance prevents dead components; decorrelation prevents redundancy.
The paper proposes new cross-correlators using Price's Theorem and piecewise-linear decomposition.
problem Optimal method for estimating cross-correlations using finite samples.
method General mathematical framework using Price's Theorem and piecewise-linear decomposition.
result Some cross-correlators based on Huber's loss functions, MP functions, and LSE functions have higher SNR.
It is shown that, on a compact Kahler manifold with boundary, the singularities of the pluricomplex Green's function with multiple poles can be prescribed to be of the form log∑j=1n∣fj(z)∣2 at each pole, where fj(z) are arbitrary local holomorphic functions with the pole as their only common zero. The pr…
We propose a novel data-driven method to learn a mixture of multiple kernels with random features that is certifiabaly robust against adverserial inputs. Specifically, we consider a distributionally robust optimization of the kernel-target alignment with respect to the distribution of training samples over a distributi…
Paper estimates differences in conditional independence graphs from time-dependent data.
problem Estimating changes in conditional dependencies between two time series with known similar structure.
method Penalized D-trace loss function approach in the frequency domain, using Wirtinger calculus, with convex and non-convex penalties.
result Established sufficient conditions for consistency and graph recovery in high-dimensional settings.
In this paper, we study the effect of different regularizers and their implications in high dimensional image classification and sparse linear unmixing. Although kernelization or sparse methods are globally accepted solutions for processing data in high dimensions, we present here a study on the impact of the form of r…
Information-theoretic measures such as the entropy, cross-entropy and the Kullback-Leibler divergence between two mixture models is a core primitive in many signal processing tasks. Since the Kullback-Leibler divergence of mixtures provably does not admit a closed-form formula, it is in practice either estimated using …
Framework improves risk neutral density estimation in illiquid markets.
problem Challenges in estimating Risk Neutral Density in illiquid markets.
method Introduces Deep Log-Sum-Exp Neural Network leveraging Deep and Transfer learning.
result Framework recovers Risk Neutral Density with few option quotes in severe illiquidity.
Support vector machines (SVMs) with sparsity-inducing nonconvex penalties have received considerable attentions for the characteristics of automatic classification and variable selection. However, it is quite challenging to solve the nonconvex penalized SVMs due to their nondifferentiability, nonsmoothness and nonconve…
Paper estimates differences in multi-attribute Gaussian graphical models using non-convex penalties.
problem Estimating differences in multi-attribute Gaussian graphical models with similar structure.
method Penalized D-trace loss function with non-convex (log-sum and SCAD) penalties, proximal gradient descent methods.
result Theoretical analysis and numerical examples support consistency in support recovery and estimation.
Extends DAMs to Gaussian distributions for efficient pattern storage and retrieval.
problem Limited storage capacity and retrieval methods for non-vector pattern representations.
method Introduces a log-sum-exp energy function over Gaussian distributions, using optimal transport maps for retrieval dynamics.
result Proves exponential storage capacity and provides quantitative retrieval guarantees.
Proposes a new sampling policy for ranking and selection problems.
problem Improving ranking and selection in adaptive sampling policies.
method Annealed entropic allocation, using soft-min weights and saddlepoint corrections.
result Consistently competitive performance in various settings.
FEM improves attention mechanisms by applying value-driven log-linear tilts.
problem Standard attention mechanisms read via convex average, limiting channel-wise selection.
method Free Energy Mixer (FEM) applies a value-driven, per-channel log-linear tilt to a fast prior over indices.
result FEM outperforms strong baselines on NLP, vision, and time-series tasks.
A new associative memory uses Sinkhorn divergence for efficient pattern retrieval.
problem Efficiently retrieving patterns from large datasets of weighted point clouds.
method Derived retrieval dynamics as a SHK gradient flow, discretized for a deterministic algorithm.
result Proved basin invariance, geometric convergence, and robust recovery from perturbations.
New method improves robustness of Bayesian experimental design.
problem Bayesian experimental design's sensitivity to prior distribution changes.
method Introduces robust expected information gain (REIG) and uses KL-divergence ambiguity sets.
result REIG stabilizes sampling-based EIG estimation and compensates for prior variability.
Annealed Entropic Allocation improves ranking and selection by mitigating hard switching and improving finite-budget discrimination.
problem Sequential budget allocation in ranking and selection
method Annealed weighted soft-min framework
result Surrogate converges uniformly to the hard minimum, soft-min weights concentrate on active challengers, and target allocation map is continuous.
The most widely used technology to identify the proteins present in a complex biological sample is tandem mass spectrometry, which quickly produces a large collection of spectra representative of the peptides (i.e., protein subsequences) present in the original sample. In this work, we greatly expand the parameter lear…
Unified analysis for graph learning from multi-attribute Gaussian time series.
problem Estimating conditional independence graph from multi-attribute Gaussian time series data.
method Unified theoretical analysis using a penalized log-likelihood objective function in the frequency domain.
result Established sufficient conditions for consistency and graph recovery in high-dimensional settings.
Proposes methods to identify and estimate counterfactual distributions with confounding.
problem Estimating counterfactual distributions in the presence of confounding.
method Nonparametric identification and semiparametric estimation using conditional copulas and machine learning.
result Valid inference for individual-level effects and nonparametric identifiability of latent confounding subspace.
To ensure stability of learning, state-of-the-art generalized policy iteration algorithms augment the policy improvement step with a trust region constraint bounding the information loss. The size of the trust region is commonly determined by the Kullback-Leibler (KL) divergence, which not only captures the notion of d…
Study risk-sensitive market making with entropy regularization for better quote control.
problem Risk-sensitive market making with exponential utility and penalties.
method Entropy-regularized certainty-equivalent Bellman policies for discrete-time market dynamics.
result Proves convergence and performance bounds for entropy-regularized policies.
Paper proves impossible for large language models to control hallucinations without sacrificing other properties.
problem Achieving truthful knowledge representation, semantic information conservation, and knowledge-constrained optimality simultaneously in large language models.
method Modeling inference as an auction of ideas, using mechanism design, proper scoring rules, and transformer architecture analysis.
result No LLM can simultaneously achieve all four essential properties without violating at least one.
This paper analyzes deep and wide transformer training dynamics.
problem Understanding the training dynamics of infinitely deep and wide transformers.
method Develops a mean-field framework for gradient-based training of transformers, controlling a neural PDE.
result Establishes a rigorous foundation for gradient-based transformer training, proving convergence to global minima.