Prediction suffix trees (PST) provide an effective tool for sequence modelling and prediction. Current prediction techniques for PSTs rely on exact matching between the suffix of the current sequence and the previously observed sequence. We present a provably correct algorithm for learning a PST with approximate suffix…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “suffix averaging”
Paper proposes GANs for generating business process suffixes and remaining times.
problem Generating accurate suffixes and remaining times for business process models.
method Encoder-decoder GAN architecture with Gumbel-Softmax distribution for categorical sequences.
result The approach outperforms baselines in suffix and remaining time prediction accuracy.
New averaging strategy achieves optimal convergence rate with high probability.
problem Optimizing convergence rate for strongly-convex functions.
method Simple non-uniform averaging strategy combined with Freedman's inequality.
result Achieves optimal convergence rate with high probability.
Improved stochastic gradient descent analysis for non-smooth convex functions.
problem Minimizing non-smooth, non-differentiable convex functions.
method Stochastic gradient descent with suffix averaging method analysis.
result Error rate of final iterate is with high probability.
Shorter adversarial prompts help protect LLMs from jailbreak attacks.
problem Protecting large language models from jailbreak attacks with long adversarial suffixes.
method Adversarial training on shorter adversarial suffixes to defend against longer adversarial suffixes.
result Aligning LLMs on shorter adversarial suffixes can effectively defend against jailbreak attacks with longer suffixes.
Recurrent neural networks have become ubiquitous in computing representations of sequential data, especially textual data in natural language processing. In particular, Bidirectional LSTMs are at the heart of several neural models achieving state-of-the-art performance in a wide variety of tasks in NLP. However, BiLSTM…
Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classical analysis usually required non-trivial smoothness assumptions, which do not apply to many modern applications of SGD with non-smooth object…
Observer learns optimal policy from learner's actions without rewards.
problem Learning optimal policy from non-rewarded actions of a non-stationary learner.
method Two-Phase Suffix Imitation framework.
result Observer achieves convergence rate of .
We present Optimal Completion Distillation (OCD), a training procedure for optimizing sequence to sequence models based on edit distance. OCD is efficient, has no hyper-parameters of its own, and does not require pretraining or joint optimization with conditional log-likelihood. Given a partial sequence generated by th…
Graph neural network predicts natural paths in graphs.
problem Predicting natural paths in graphs.
method Graph Neural Network (Gretel) for path extrapolation.
result Gretel efficiently predicts and samples from future path distributions.
SGLBO optimizes quantum circuits with fewer measurements, improving accuracy and noise resilience.
problem Efficiently optimizing parameterized quantum circuits with reduced measurement shots and noise.
method Developed SGLBO combining SGD and BO, with adaptive measurement-shot strategy and suffix averaging.
result Significantly reduces measurement-shot cost while improving accuracy and noise resilience.
CROP verifies clean prefixes in reasoning traces, improving downstream repair accuracy.
problem Uncertainty in reasoning traces prevents full certification of entire responses.
method CROP selects a calibrated threshold to certify the longest prefix with low risk proxies.
result CROP improves downstream repair accuracy by preserving valid reasoning and discarding misleading suffixes.
Ultra-fast search algorithm for trillion-scale corpora with semantic flexibility.
problem Efficiently searching over large natural language corpora with semantic variations.
method String matching based on suffix arrays, vector representation of words, dynamic corpus-aware pruning, fast exact lookup.
result Substantially lower search latency compared to existing methods on FineWeb-Edu corpus.
Improved Last-Iterate Convergence of Shuffling Gradient Methods for Nonsmooth Convex Optimizationmath.OC
Improved shuffling gradient methods converge faster for nonsmooth convex optimization.
problem Improving convergence rates for nonsmooth convex optimization problems.
method Analysis of shuffling gradient methods, focusing on Random Reshuffle and Single Shuffle strategies.
result Shuffling gradient methods, particularly Random Reshuffle and Single Shuffle, converge faster than Proximal Gradient Descent for nonsmooth convex optimization.
Part-of-speech (POS) tagging is a fundamental component for performing natural language tasks such as parsing, information extraction, and question answering. When POS taggers are trained in one domain and applied in significantly different domains, their performance can degrade dramatically. We present a methodology f…
Directional Kernel Mean Difference: A Fast Signed Statistic for Univariate Distribution Comparisonstat.ML
DKMD is a fast signed statistic for comparing univariate distributions.
problem Comparing univariate distributions, especially preserving directionality.
method DKMD integrates kernel mean embeddings against an odd weighting function.
result DKMD preserves directionality and is robust to outliers.
New HMC method handles features in POS tagging, outperforming MEMM.
problem HMC struggles with arbitrary features in POS tagging.
method Introduced Entropic Forward-Backward (EFB) probabilities to compute HMC restorations.
result EFB-based HMC outperforms MEMM in POS tagging.
Online monitoring system for safety classifiers with shift detection and conformal adaptation
problem Detecting and adapting to distributional shifts in deployed safety classifiers
method Calibrated sequential statistics for online monitoring, conformal abstention for adaptation
result 86.6% valid detection with mean latency of 39.5 steps
Algorithm learns to bid in auctions with shilling, masking real bids.
problem Learning to bid in auctions manipulated by shilling.
method Combines interval-elimination and optimistic branches, debiases losing-side reports.
result Achieves dynamic-pricing rate and first-price auctions rate .
Improved reasoning model by sampling from power distribution without additional training.
problem Efficiently sampling from a sharpened distribution to improve reasoning models.
method Entropy-Cut Metropolis-Hastings algorithm that identifies key decision points for resampling.
result The method consistently improves reasoning models across various datasets.
Proposes two techniques for efficient tail averaging in streams.
problem Efficiently averaging the last examples in a stream with low memory and constant access.
method Two techniques with low constant memory cost and access to average at every time step. Improved accuracy at higher memory cost.
result Proposes techniques for efficient tail averaging with constant memory and access at every time step.
Improved estimation of VAR-Moving Average models using GLS.
problem Estimating VAR-Moving Average models efficiently.
method Use generalized least squares (GLS) for each fixed moving average polynomial.
result Likelihood function format similar to VAR models, allowing maximum likelihood estimation.
New RL algorithms improve average-reward performance.
problem Improving RL algorithms for average-reward criteria.
method Developed novel algorithms addressing average-reward criterion directly.
result ATRPO significantly outperforms TRPO in challenging MuJuCo environments.
Partial model averaging improves Federated Learning performance.
problem Periodic model averaging causes significant model discrepancy in Federated Learning.
method Proposes a partial model averaging framework that encourages local models to stay close to each other.
result Partial averaging achieves up to 2.2% higher validation accuracy than full averaging.
Paper introduces stability in model averaging and proposes a L2-penalty method.
problem Theoretical properties of model averaging from stability perspective.
method Introduces stability, defines asymptotic empirical risk minimizer, and proposes L2-penalty model averaging method.
result Proposed L2-penalty method ensures stability and consistency under reasonable conditions.
Explains the difference between EMA and moving EMA, focusing on market trend indicators.
problem Understanding the difference between exponential moving average and moving exponential average.
method Explains the mathematical tools and definitions of trend indicators.
result Discusses the properties of the MACD indicator and its use in market trend analysis.
Simple adaptive attacks can jailbreak state-of-the-art safety-aligned language models.
problem Vulnerability of safety-aligned language models to simple adaptive attacks.
method Designing adversarial prompt templates, random search on suffixes, and transfer/prefilling attacks.
result 100% attack success rate on various models including GPT-4, Vicuna, Mistral, and Claude.
New bounds for average graph distance using curvature and centrality.
problem Finding bounds for average graph distance.
method Using weighted average Ollivier curvature with edge betweenness centrality.
result Equality in bounds achieved for specific reflective graphs.
PACE optimizes training for averaged language models, improving performance.
problem How to optimize training for averaged language model iterates.
method Formulated as an optimal-control problem, solved for minimizing error of the average with a penalty on intervention size.
result PACE improves the limiting squared error of the iterate-average estimator by an arbitrarily large factor on some instances.
Increasing iterate averaging improves convergence rates for saddle-point problems.
problem Solving saddle-point problems efficiently.
method Increasing iterate averaging schemes applied to various first-order methods.
result Increasing iterate averaging preserves the convergence rate with no additional assumptions or overhead.
Paper explores weighted averaging schemes for SGD, achieving asymptotic normality and optimality.
problem Improving convergence of SGD in various settings.
method Develops a general weighted averaging scheme for SGD and establishes asymptotic normality.
result Establishes asymptotic normality and optimality of weighted averaged SGD solutions.
In mixture model-based clustering applications, it is common to fit several models from a family and report clustering results from only the `best' one. In such circumstances, selection of this best model is achieved using a model selection criterion, most often the Bayesian information criterion. Rather than throw awa…
Two-Tailed Averaging improves generalization by optimizing the number of leading iterates to ignore.
problem Improving generalization in stochastic optimization with limited resources and hyperparameters.
method An anytime adaptive algorithm that balances the number of leading iterates to ignore for better generalization.
result Approximates the optimal tail at all optimization steps, improving generalization without hyperparameters.
The study examines how average scalar curvature influences geometric properties of Riemannian manifolds.
problem Investigating the geometric properties of Riemannian manifolds influenced by average scalar curvature.
method Analyzing the conjugate radius, average area of geodesic spheres, average volume of metric balls, and total volume of closed manifolds.
result Improves the Bishop-Gromov estimate on the average volume of metric balls and proves monotone decreasing properties of certain geometric integrals.
New moving average adapts weight dynamically based on polynomial and wavefunction.
problem Lagging traditional moving averages in adjusting to changes in data.
method Develops a moving average with weight as a polynomial of a wavefunction from an eigenproblem.
result Immediate 'switch' without lag, adapting to changes in data.
New TD method stabilizes average-reward learning.
problem Stability issues in average-reward TD learning.
method Implicit fixed point update for average-reward TD().
result Improved numerical stability and broader step-size range.
We analyze the question whether sliding window time averages applied to stationary increment processes converge to a limit in probability. The question centers on averages, correlations, and densities constructed via time averages of the increment x(t,T)=x(t+T)-x(t)and the assumption is that the increment is distribute…
Nested model averaging improves high-dimensional linear regression performance.
problem High-dimensional linear regression with predictor ordering impact.
method Combining model averaging with regularized estimators on the solution path.
result Nested model averaging with lasso and SLOPE outperforms competing methods.
Average Oracle outperforms DCC+NLS in portfolio optimization.
problem Optimizing portfolio performance in volatile markets.
method Comparing the Average Oracle to various DCC+NLS variants.
result The Average Oracle consistently yields higher Sharpe ratios.
Study irregular behavior of ball averages for non-amenable group actions on foliations.
problem Exploring irregular behavior of ball averages for non-amenable group actions.
method Introducing a new mechanism based on group structure to analyze irregular behavior.
result First examples of codimension one foliations with non-existent length averages.
Paper explores how combining tail-averaging and minibatching improves SGD convergence.
problem Understanding and optimizing learning properties of SGD variants.
method Least squares learning in a nonparametric setting, focusing on multiple passes, mini-batching, and averaging.
result Tail averaging allows faster convergence rates than uniform averaging in nonparametric settings.
WASH trains ensembles with shuffled weights to improve accuracy and reduce communication.
problem Training ensembles for weight averaging leads to models converging to different loss basins.
method WASH randomly shuffles a small percentage of weights during training to keep models within the same basin.
result WASH achieves state-of-the-art image classification accuracy with lower communication costs.
Average signature measures geodesics in Lie groups.
problem Understanding geometric properties of Lie groups through geodesic paths.
method Introducing average signature and using it with trace operation to recover geometric properties.
result Average signature can recover geometric properties like dimension, diameter, volume, and scalar curvature.
Improving optimization for iterate-averaged language models
problem How to optimize the averaged model returned by Language Model pipelines
method Formulating optimizer design as an optimal-control problem
result Proven convergence rate and strict improvement in squared error
Asymptotics for the Discrete-Time Average of the Geometric Brownian Motion and Asian Optionsq-fin.PR
The time average of geometric Brownian motion plays a crucial role in the pricing of Asian options in mathematical finance. In this paper we consider the asymptotics of the discrete-time average of a geometric Brownian motion sampled on uniformly spaced times in the limit of a very large number of averaging time steps.…
In this thesis, we consider the suitability of using the charged cold fluid model in the description of ultra-relativistic beams. The method that we have used is the following. Firstly, the necessary notions of kinetic theory and differential geometry of second order differential equations are explained. Then an averag…
Improved averaging method for noisy observations converges strongly.
problem Noisy observations from random dynamical systems require stable estimates.
method Introduced -EMA, a modified exponential moving average with subharmonic weight decay.
result Stochastic convergence guarantees for -EMA under mild assumptions.
Nonsmooth High-Order Averaging Theory with Application to Extremum Seeking Optimization and Controlmath.OC
New theory for nonsmooth systems helps optimize and control complex functions.
problem Optimizing and controlling systems with nonsmooth functions.
method Higher-order averaging theory with nonsmooth near-identity transformation and lexicographic differentiation.
result Closed formula for nonsmooth first and second-order averaging.