Improves SA-CCR model to be more consistent and risk-sensitive.
problem Inconsistent and risk-insensitive SA-CCR model.
method Cashflow decomposition in a 3-Factor Gaussian Market Model.
result Makes SA-CCR self-consistent and risk-sensitive.
Study on nonsmooth contractive SA with constant stepsize and Q-learning.
problem Understanding convergence and bias in nonsmooth contractive SA with different noise types.
method Proposed prelimit coupling technique for steady-state convergence and derived asymptotic bias.
result Asymptotic bias of nonsmooth SA is proportional to the square root of the stepsize.
Study classifies Persian speech acts for better understanding of text intent.
problem Understanding the intended function of Persian texts.
method Dictionary-based statistical technique using WordNet for SA recognition.
result Proposed method achieved state-of-the-art accuracy of 0.95 for Persian SA classification.
Deep neural networks automate statistical analysis for big data.
problem Challenges in applying statistical analysis to big data.
method Constructing CNNs for automatic model selection and parameter estimation.
result CNNs demonstrate excellent performance in automatic model selection and estimation.
Super learning in SAS matches R package performance in various tasks.
problem Improving machine learning performance in SAS.
method Developed a new SAS macro for super learning, comparing it to R package performance.
result SAS macro performs similarly to R package across simulated and real datasets.
This paper analyzes the conflict between Hamming loss and subset accuracy in multi-label classification.
problem The conflict between Hamming loss and subset accuracy in multi-label classification.
method The paper analyzes the learning guarantees of algorithms optimizing Hamming loss and subset accuracy, providing theoretical bounds and experimental support.
result Optimizing Hamming loss with its surrogate loss can lead to good performance on subset accuracy in small label spaces, contrary to theoretical expectations.
SAWAR improves SA models by making them more robust to data uncertainties.
problem Improving survival analysis models' robustness to data uncertainties.
method Adversarial robustness through Min-Max optimization with CROWN-IBP.
result SAWAR outperforms baseline methods and SOTA models across various metrics.
Overview of non-stochastic-gradient SA algorithms in signal processing and ML.
problem Dealing with large data sets and uncertainties in signal processing and machine learning.
method General framework of SA algorithms using Lyapunov functions.
result Unified convergence properties of non-stochastic-gradient algorithms.
Paper analyzes convergence of decentralized algorithms with noise and bias.
problem Finite time convergence analysis of decentralized stochastic approximation schemes.
method Separated iterates into consensual parts and consensus error; bounded consensus error in terms of stationarity.
result Decentralized SA scheme converges at O ( log T / T ) {\cal O}(\log T/ \sqrt{T} ) O ( log T / T ) rate. Paper compares two possibilistic segmentation methods for SAS imagery.
problem Segmenting synthetic aperture sonar images into different seafloor environments.
method Comparison of Possibilistic Fuzzy Local Information C-Means (PFLICM) and Possibilistic K-Nearest Neighbors (PKNN) algorithms.
result PKNN outperforms PFLICM in segmentation performance on SAS images.
EvoMSA unifies multilingual sentiment analysis systems.
problem Multilingual sentiment analysis in various languages.
method Genetic Programming-based classifier combining multiple text classifiers.
result EvoMSA performs competitively in multiple sentiment analysis competitions.
This paper approximates SA iterates using Gaussian distributions for tail bounds.
problem Characterizing the distribution of stochastic approximation iterates in finite time.
method Approximating pre-limit distributions of SA iterates by Gaussian sequences with recursively defined covariances.
result Explicit bounds on the Wasserstein-1 distance between rescaled iterates and Gaussians.
SA-PEF improves federated learning efficiency by correcting gradient mismatches.
problem Slow decay of residual error in federated learning under non-IID data.
method Integrates step-ahead correction with partial error feedback.
result Achieves faster convergence and target accuracy compared to standard EF.
SA-GFN corrects biases in GFlowNets due to graph symmetries.
problem Systematic biases in state transition probability computations.
method Incorporates symmetry corrections into the learning process through reward scaling.
result Eliminates need for explicit state transition computations.
New research shows SAA can outperform SA for Wasserstein barycenters.
problem Optimizing Wasserstein barycenters with entropy regularization.
method Comparison of Stochastic Approximation (SA) and Sample Average Approximation (SAA) for large-scale problems.
result SAA can be more efficient than SA for Wasserstein barycenters, especially in large-scale settings.
SA-Solver improves stochastic sampling from DPMs.
problem Efficient sampling from Diffusion Probabilistic Models (DPMs) is time-consuming.
method Proposes SA-Solver, an improved stochastic Adams method for solving diffusion SDE.
result SA-Solver achieves improved or comparable performance compared to SOTA methods for few-step sampling.
A new TS-SA method alleviates non-stationarity in TS algorithms for bandits.
problem Non-stationarity in existing TS algorithms for multi-armed bandits.
method Integrates stochastic approximation within TS framework, using Langevin Monte Carlo and SA steps.
result Establishes near-optimal regret bounds for TS-SA, with simplified analysis.
Polyak-Ruppert CLT for SA-Adam with momentum and non-convergent adaptive preconditioning
problem Adaptive optimizers combining momentum and non-convergent preconditioning
method Proving positive drift stability and a non-autonomous Polyak-Ruppert CLT for SA-Adam
result The iterate-marginal covariance is exactly the plain stochastic gradient descent (SGD) sandwich
The paper analyzes convergence of Riemannian SA schemes for stochastic optimization.
problem Stochastic optimization problems on Riemannian manifolds.
method Analyzes convergence of Riemannian stochastic approximation schemes using exponential map or retraction functions.
result Shows Riemannian SA schemes find an O ( b ∞ + log n / n ) {\mathcal{O}}(b_\infty + \log n / \sqrt{n}) O ( b ∞ + log n / n ) -stationary point within O ( n ) {\mathcal{O}}(n) O ( n ) iterations. This study improves convergence of two-timescale SA under Markovian noise in reinforcement learning.
problem Stability and convergence of two-timescale stochastic approximations under Markovian noise.
method Introduced a new control strategy for the fast timescale parameter.
result Established almost sure convergence of TDC with eligibility traces under off-policy learning with linear function approximation.
New method reduces regret for sparse adversarial SSP problems.
problem Sparse adversarial Stochastic Shortest Path problem.
method Proposed ℓ r \ell_r ℓ r -norm regularizers for adaptive sparsity. result Regret scales with log M \sqrt{\log M} log M instead of log S A \sqrt{\log SA} log S A . NODEs with explicit time dependence can interpolate and generalize like piecewise-constant estimators.
problem Learning from finite datasets with neural ODEs.
method Control-theoretic perspective applied to semi-autonomous NODEs.
result SA-NODEs can interpolate and satisfy SCC, leading to generalization rates similar to histogram and nearest-neighbor estimators.
SA-ABR uses UAV sensor data to optimize video streaming quality.
problem Dynamic UAV flight states cause fluctuating video streaming quality.
method SA-ABR integrates sensor data with network observations to train a DRL model.
result SA-ABR outperforms existing ABR algorithms by 21.4% in QoE.
New method for asynchronous stochastic approximation converges in reinforcement learning.
problem Finding solutions to equations with noisy measurements in reinforcement learning.
method Batch Asynchronous Stochastic Approximation (BASA) with conditions for convergence and rate of convergence.
result Sufficient conditions for convergence and rate of convergence of BASA.
Paper proves a spinorial version of Aubin's estimate for the Yamabe problem.
problem Solving the Yamabe problem for spin manifolds.
method Spinorial approach using the Dirac operator and conformal metrics.
result Shows a spinorial analogue to Aubin's estimate for the Yamabe problem.
Adjoint SA speeds up bioprocess parameter learning.
problem Challenges in digital twin development for biomanufacturing.
method Adjoint sensitivity analysis on multi-scale enzymatic reaction networks.
result Resilient sensitivities reveal bioprocess regulatory mechanisms.
Optimizes learning policies in MDPs with weakly communicating structure.
problem Learning optimal policies in weakly communicating MDPs with generative model.
method Span-based approach, reducing to discounted MDPs for analysis.
result First minimax optimal sample complexity bound for weakly communicating MDPs.
SA-FDR uses simulated annealing for feature selection in high-dimensional data.
problem Feature selection in high-dimensional datasets with high predictive accuracy.
method Simulated Annealing for combinatorial optimisation of feature subsets.
result SA-FDR selects more compact feature subsets with high predictive accuracy.
This work relaxes energy constraints in self-attention layers for a more general analysis.
problem Understanding inherent biases and dynamics in self-attention layers without energy functions.
method Dynamical systems analysis and Jacobian matrix examination.
result Normalized dynamics are close to a critical state, indicating high inference performance.
New stability and convergence conditions for asynchronous SAs with biased approximations.
problem Stability and convergence issues in asynchronous SAs with biased approximation errors.
method Verifiable sufficient conditions for stability and convergence of asynchronous SAs with asymptotically biased errors.
result Stability of asynchronous SAs is unaffected by asymptotically bounded biased approximation errors.
Paper analyzes SA for fixed-point equations with noise, establishing convergence rates.
problem Solving fixed-point equations with noisy data.
method Uses smooth convex envelopes to construct Lyapunov functions and show negative drift.
result Establishes first-known convergence rate for V-trace algorithm in RL.
Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
problem Minimax estimators may be inadmissible under structure-agnostic models.
method Exhibit second-order (U-statistic) estimators that asymptotically dominate DML estimators.
result Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
RLD improves combinatorial optimization by avoiding local minima.
problem Efficiently solving combinatorial optimization problems.
method Regularized Langevin Dynamics (RLD) for combinatorial optimization.
result RLD achieves comparable or better performance than previous methods.
Single-timescale analysis improves convergence in multi-sequence stochastic approximation.
problem Finite-time convergence of nonlinear stochastic approximation with multiple coupled sequences.
method Smoothness property of fixed points and analysis of fine-grained single-timescale SA.
result Improved iteration complexity for achieving ε-accuracy in multi-sequence single-timescale SA.
We analyze SA with Markovian data and nonlinear updates, overcoming prior limitations.
problem Analyzing stochastic approximation with Markovian data and nonlinear updates.
method Fine-grained analysis of SA iterates and Markovian data, leveraging smoothness and recurrence properties.
result Established weak convergence and precise asymptotic bias of SA iterates.
Stochastic approximation extended to infinite dimensions, especially Banach spaces.
problem Applying stochastic approximation to infinite-dimensional spaces, particularly Banach spaces.
method Extending stochastic approximation to Banach spaces, including cases like C ( [ 0 , 1 ] , R d ) C([0,1],\mathbb{R}^d) C ([ 0 , 1 ] , R d ) and L 1 ( [ 0 , 1 ] , R d ) L^1([0,1],\mathbb{R}^d) L 1 ([ 0 , 1 ] , R d ) . result Stochastic approximation can be applied to Banach spaces, including those without the Radon-Nikodym property.
We investigate finite-time decoupled convergence in nonlinear two-time-scale stochastic approximation.
problem Achieving decoupled convergence in nonlinear two-time-scale stochastic approximation.
method Nested local linearity assumption, suitable step size selection, convergence analysis of matrix cross term, fourth-order moment convergence rates.
result Finite-time decoupled convergence rates can be achieved in nonlinear two-time-scale stochastic approximation with proper step size selection.
Paper develops bounds for stochastic approximation with averaging.
problem Establish high-probability bounds for averaged stochastic approximation.
method Develops a general framework for non-asymptotic concentration bounds.
result Derives sharp bounds for averaged iterates and tightens existing results.
New RL algorithms handle stochastic action sets, addressing divergence issues.
problem Handling stochastic action sets in reinforcement learning.
method Developed new policy gradient algorithms with variance reduction techniques.
result Proved conditions for convergence of new algorithms.
Develops a SAS approach for high-dimensional risk prediction using unlabeled data.
problem Challenges in risk modeling with EHR data due to lack of direct disease outcomes and high dimensionality.
method Surrogate Assisted Semi-supervised Learning (SAS) approach leveraging unlabeled and labeled data.
result Valid inference for predicted risk even when underlying model is dense and mis-specified.
Improved GP decoder training with SAS approximations.
problem Training expensive Gaussian process decoders is challenging and computationally expensive.
method Developed a new stochastic estimate of log-marginal likelihood based on cross-validation.
result SAS-GP improves robustness and reduces computational cost compared to variational autoencoders.
Paper improves stochastic bilevel optimization methods for highly-smooth problems.
problem Finding ε ε ε -stationary points in stochastic bilevel optimization. method Proposes F 2 {}^2 2 SA- p p p methods using p p p th-order finite differences for hyper-gradient approximation. result Achieves upper complexity bound of i l d e O ( p ε − 4 − p / 2 ) ilde{\mathcal{O}}(p ε^{-4-p/2}) i l d e O ( p ε − 4 − p /2 ) for p p p th-order smooth problems. This book teaches differential geometry of curves and surfaces in 3D Euclidean space.
problem Understanding differential geometry concepts for mathematics and sciences students.
method Covering definitions, ideas, and concepts with examples and illustrations.
result Successful understanding and application of differential geometry.
A new Shapley value approach for neural networks interpretable and stable.
problem Neural networks' interpretability and training stability issues.
method Shapley value approximation for ReLU activation, globally continuous Shapley gradient, Shapley Activation function.
result SA consistently outperforms ReLU in training convergence, accuracy, and stability.
SSRCA simplifies ABM sensitivity analysis using machine learning.
problem Hardness of performing sensitivity analysis for complex ABMs.
method Machine learning pipeline (Simulate, Summarize, Reduce, Cluster, Analyze) for ABMs.
result SSRCA identifies sensitive parameters and common output patterns for ABMs.
This paper reviews sentiment analysis on Indian languages.
problem Understanding sentiment in multilingual web data.
method Reviews and discusses approaches for sentiment analysis on Indian languages.
result Challenges in sentiment analysis on indigenous languages.
Paper proves convergence of SA algorithm via martingale and converse Lyapunov methods.
problem Proves convergence of stochastic approximation algorithm.
method Uses martingale and converse Lyapunov methods to prove convergence.
result Provides alternate proof of convergence for SA algorithm.
Analyzes a non-asymptotic SA scheme for non-convex, smooth objectives.
problem Analyzes SA schemes under relaxed assumptions for non-convex, smooth objectives.
method General SA scheme with state-dependent drift and mean field not necessarily gradient type.
result Analyzes the online EM algorithm and policy-gradient method for reinforcement learning.