New bounds on continuous random variables' right-tail probabilities.
problem Finding precise upper and lower limits for right-tail probabilities of continuous random variables.
method Developed new bounds based on PDF, first derivative, and two parameters.
result The new bounds are tight for various continuous random variables.
Improved bounds for discrete probability distribution estimation under the ℓ∞ norm.
problem Estimating discrete probability distributions under the ℓ∞ norm with improved bounds.
method Minimax bounds in expectation and high-probability tail bounds.
result Resolved open questions posed in Kontorovich and Painsky (JMLR, 2025), including a fully empirical tightest risk bound and identifying the worst-case extremal distribution.
New bounds for LDP with heterogeneous privacy levels guaranteeing high probability of accuracy.
problem Statistical estimation under LDP with users having varying privacy levels.
method Developed finite sample upper bounds in ℓ_2-norm with high probability, complemented by lower bounds.
result Optimal guarantees for heterogeneous LDP in terms of probability and constants.
Recent research has made significant progress on the problem of bounding log partition functions for exponential family graphical models. Such bounds have associated dual parameters that are often used as heuristic estimates of the marginal probabilities required in inference and learning. However these variational est…
Study on the probability of immunity and its bounds.
problem Estimating the probability of immunity and its bounds.
method Derive necessary and sufficient conditions for non-immunity and ε-bounded immunity; introduce indirect immunity; propose sensitivity analysis.
result Estimate the probability of benefit and produce tighter bounds of the probability of benefit.
The paper bounds and identifies joint probabilities in causal inference with monotonicity assumptions.
problem Bounding and identifying joint probabilities of potential outcomes and observed variables under monotonicity assumptions.
method Proposes new families of monotonicity assumptions, formulates bounding problem as linear programming, introduces new monotonicity assumption for identification.
result Validated methods through numerical experiments and applied to real-world datasets.
New bounds on AE success probability in GP models.
problem Limiting the success of adversarial examples in probabilistic models.
method Investigated upper bounds on AE success probability using Gaussian Processes.
result Proved a new upper bound of AE success probability dependent on perturbation norm, kernel function, and training dataset distance.
We extend Bayes' theorem for upper probabilities considering likelihood uncertainty.
problem Addressing uncertainty in likelihood for upper probability bounds.
method Generalization of Wasserman and Kadane's result, considering both prior and likelihood uncertainty.
result A sufficient condition for the upper bound to become an equality.
A novel post-hoc calibration method reduces neural network calibration errors.
problem Neural networks produce poorly calibrated probabilities, leading to underconfidence and overconfidence.
method Probability bounding (PB) via box-constrained softmax (BCSoftmax) function.
result Consistently reduces calibration errors on four real-world datasets.
Method bounds tail probabilities of continuous RVs.
problem Bounding tail probabilities of continuous random variables.
method Setting continuous, positive, and strictly decreasing/increasing functions to derive upper and lower bounds.
result Provides tighter bounds than existing methods, including a novel asymptotic capacity bound for AWGN channel.
New Schwarz Lemma for Bergman metrics in bounded domains.
problem Finding bounds for Bergman metrics in bounded domains.
method Using Cauchy-Schwarz inequality from probability theory.
result Established a new Schwarz Lemma for Bergman metrics.
The study tightens bounds on binomial probabilities and minimums using KL-divergence.
problem Tightening bounds on binomial probabilities and minimums of i.i.d. Binomials.
method Applied Sanov's theorem to derive upper and lower bounds on binomial tail probabilities and minimums, expressed in terms of KL-divergence.
result High probability upper and lower bounds on the minimum of i.i.d. Binomial random variables, finite sample, asymptotically tight.
We give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value. The inequality plays an important role in a variety of contexts, including the analysis of relative deviation bounds in learning theory and generalization bounds for unbounded loss functions.
Study on covering probability of random balls in bounded open sets.
problem Probability of covering a bounded open set E with random balls of radius δ. method Geometric conditions and partition of E; lower bounds using good partitions. result Lower bounds to the probability of covering E with balls tend to 1 as Nexp(−δn). New bounds use IPMs to improve generalization in machine learning.
problem Improving generalization bounds in machine learning.
method PAC-Bayes bounds with Integral Probability Metrics (IPM).
result Natural interpolation between worst-case and favorable cases.
Sharp bounds for high-probability estimation of discrete distributions.
problem Estimating discrete distributions with high probability under χ2-divergence. method Sharp upper and lower bounds for the classical Laplace estimator, and characterization of minimax high-probability risk for any estimator.
result Sharp bounds for high-probability estimation of discrete distributions can be achieved through a simple smoothing strategy.
Dynamic Vocabulary Pruning stabilizes LLM training by removing low-probability tokens.
problem Training Large Language Models (LLMs) with Reinforcement Learning (RL) causes numerical divergence between inference and training.
method Dynamic Vocabulary Pruning (DVP) constrains the RL objective to a safe vocabulary that excludes low-probability tokens.
result DVP stabilizes training by reducing systematic bias introduced by the extreme tail of the token distribution.
New approach for online learning with adaptive adversaries, simpler and more effective.
problem Online learning with adaptive adversaries, especially in bandits and MDPs.
method Uses standard unbiased estimators and a simple increasing learning rate schedule, aided by logarithmically homogeneous self-concordant barriers and strengthened Freedman's inequality.
result First high-probability regret bounds for adversarial bandits and MDPs, resolving open problems.
Study minimax regret in sequential probability assignment with and without side information.
problem Minimax regret analysis in sequential probability assignment.
method Upper and lower bounds on minimax regret using square-root entropy.
result Lower bound matches upper bound for Donsker classes, up to log factors.
New method bounds stochastic subgradient methods with heavy-tailed noise.
problem Bounding stochastic subgradient methods under heavy-tailed noise.
method Clipped version of projected stochastic subgradient method.
result Near optimal any-time and finite horizon bounds for averaging schemes.
The softmax representation of probabilities for categorical variables plays a prominent role in modern machine learning with numerous applications in areas such as large scale classification, neural language modeling and recommendation systems. However, softmax estimation is very expensive for large scale inference bec…
The paper provides bounds for LSA with fixed stepsizes under random estimates.
problem Analyzing the performance of LSA algorithms with fixed stepsize.
method Non-asymptotic analysis based on new results about matrix moments and high probability bounds.
result Derives high probability bounds on LSA performance under weaker conditions than previous works.
A method for diffusion on probability simplex for generative models.
problem Tension between continuous and discrete data in diffusion models.
method Proposes using softmax function applied to Ornstein-Uhlenbeck Process on probability simplex.
result Method extends to bounded image generation.
Improved matrix completion for non-uniformly sampled data.
problem Estimating unobserved entries in a matrix with varying sampling probabilities.
method Developed entry-specific bounds for low-rank matrix completion under structured non-uniform sampling.
result Error bounds for each entry match minimax lower bounds under certain conditions.
Unified high-probability regret bounds for online convex optimisation with randomised gradient estimators.
problem Online convex optimisation with randomised gradient estimators for ℓq-Lipschitz losses. method FTRL with randomised two-point finite-difference gradient estimators based on cone-measure sampling from ℓr-spheres. result Unified high-probability regret bounds for all p,q,r∈[1,∞]. Paper finds how many neurons are needed to approximate histogram distributions.
problem How many neurons are needed to approximate a target probability distribution?
method Examined for uniform input distribution and histogram target distributions, using efficient neural net construction.
result Obtained a new upper bound on the number of required neurons, strictly better than previous bounds.
Upper bound for max-sliced 2-Wasserstein distance between measures.
problem Estimating distance between probability measures and their empirical counterparts.
method Same technique as previous work, upper bound approach.
result Upper bound for expected max-sliced 2-Wasserstein distance.
New method tightens bounds on causation probabilities using independent datasets.
problem Challenging point identification of causation probabilities without strong assumptions.
method Imposes counterfactual consistency between SCMs constructed from independent datasets and uses conditional mutual information.
result Significantly tighter bounds on causation probabilities are established.
We study two-layer belief networks of binary random variables in which the conditional probabilities Pr[childlparents] depend monotonically on weighted sums of the parents. In large networks where exact probabilistic inference is intractable, we show how to compute upper and lower bounds on many probabilities of intere…
Probabilistic bounds on neuron death in deep networks, showing depth can be increased indefinitely.
problem Understanding neuron death in deep rectifier networks and its impact on model trainability.
method Deriving upper and lower bounds on neuron death probability as a function of model hyperparameters.
result The probability of neuron death decreases as network depth increases, provided width increases proportionally.
Study on error probability for classification of heavy-tailed renewal processes.
problem Error probability in classification of heavy-tailed renewal processes.
method Asymptotic expressions for Bhattacharyya bound on misclassification error probabilities.
result Obtained asymptotic expressions for misclassification error probabilities.
Bayesian algorithm improves best-arm identification within fixed budget.
problem Maximizing probability of identifying optimal arm within fixed budget.
method Proposes Bayesian elimination algorithm and derives upper bound on misidentification probability.
result Upper bound on misidentification probability reflects prior quality and matches lower bound.
Sharp bounds for max-sliced Wasserstein distances derived for empirical distributions.
problem Estimating the expected max-sliced Wasserstein distance between a probability measure and its empirical distribution.
method Banach space version and operator norm approach for upper bounds.
result Upper bounds for max-sliced Wasserstein distances are essentially matching and sharp up to a log factor.
New algorithm reduces high-probability regret for time-varying feedback graphs.
problem High-probability regret bounds for adversarial bandits with time-varying feedback graphs.
method Online mirror descent framework with innovative techniques for pessimistic loss estimators.
result Achieves optimal high-probability regret bound for general and weakly observable graphs.
New error bounds for flow matching methods using deterministic sampling.
problem Improving the accuracy of flow matching methods for generating probability distributions.
method Derived error bounds for flow matching methods under deterministic sampling conditions.
result Presented error bounds for flow matching methods using L2 loss and regularity conditions. New bounds using samplewise evaluated CMI for deep neural networks.
problem Improving generalization bounds for deep neural networks.
method Introduced a new family of information-theoretic generalization bounds using samplewise evaluated conditional mutual information (CMI).
result The new bounds can be tighter than previous ones for deep neural networks.
New method for estimating median and mean with high probability privacy.
problem Estimating median and mean with differential privacy.
method Propose, Test, Release (PTR) mechanism with concentration inequalities.
result First sub-Gaussian high probability bounds for differentially private median and mean estimation.
We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability pij. Two cases are covered. (a) The one-step case, where after playing arm i the learner observes a sample reward feedback of arm j with independent prob…
Study tests if a probability measure is near a real algebraic variety.
problem Deciding if a probability measure is near a real algebraic variety.
method Proved upper bound on sample complexity, reduced to semialgebraic decision problem, studied Hausdorff geometry of real algebraic varieties.
result Upper bound on sample complexity for testing variety hypothesis.
In this paper, we consider the problem of column subset selection. We present a novel analysis of the spectral norm reconstruction for a simple randomized algorithm and establish a new bound that depends explicitly on the sampling probabilities. The sampling dependent error bound (i) allows us to better understand the …
High-probability bound for distributed stochastic approximation tracking error.
problem Analyzing the convergence of distributed stochastic approximation schemes.
method Analysis using ODE approach to stochastic approximation.
result High probability bound for tracking error between iterates and limiting differential equation.
Uniform stability of a learning algorithm is a classical notion of algorithmic stability introduced to derive high-probability bounds on the generalization error (Bousquet and Elisseeff, 2002). Specifically, for a loss function with range bounded in [0,1], the generalization error of a γ-uniformly stable learning a…
The study optimizes distribution estimation from samples with relative entropy error, adapting to sparse distributions.
problem Estimating discrete distributions with high-probability accuracy in relative entropy.
method Analysis of Laplace estimator and confidence-dependent smoothing techniques, including data-dependent smoothing.
result Optimal high-probability risk bounds for various estimators, including a new data-dependent smoothing method.
New bounds for generative models under weaker assumptions.
problem Establishing convergence guarantees for generative models under weak assumptions.
method Non-asymptotic 2-Wasserstein distance bounds for probability flow ODEs under weak log-concavity and Lipschitz continuity.
result Concrete convergence rates for generative models, including non-log-concave distributions.
New bounds show faster convergence for learning algorithms.
problem Improving risk bounds for learning algorithms.
method Using algorithmic stability and common assumptions like Polyak-Lojasiewicz condition, smoothness, and Lipschitz continuity.
result Achieves convergence rate of O(log2(n)/n2) with high probability. Paper establishes lower bounds for Gaussian process bandit optimization under various perturbation models.
problem Lower bounds for Gaussian process bandit optimization in noisy and robust settings.
method Novel proof techniques for standard and robust settings, including deterministic strategies.
result Demonstrates inevitable joint dependence of cumulative regret on corruption level and time horizon in robust settings.
Method solves complex optimization problems with high probability bounds.
problem Nonlinear equality constrained stochastic optimization problems.
method Step-search sequential quadratic programming method.
result High-probability bound on iteration complexity for first-order stationarity.
Sharp bounds found on expert error in binary advice aggregation.
problem Aggregating binary advice from conditionally independent experts.
method Sharp upper and lower bounds on optimal error probability in asymmetric case.
result Sharp bounds recover and sharpen known results in symmetric case.