Research
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.

168,657 papers · 148 categories

Trend · papers per month

4208401,2601,680 · Jun 202019922001200920172026
48 results for learning rate free

ScheduleFree+ improves large language model training without schedules or learning rates.

problem Scaling up Schedule-Free Learning to large language models.
method Learning-rate-free and schedule-free method for training large language models.
result ScheduleFree+ outperforms SOTA schedules by 31% at 1000 tokens per parameter.

Simpler, parameter-free AdaGrad and Adam variants with convergence guarantees.

problem Inefficiencies in ad-hoc learning rate tuning for optimization algorithms.
method Developed AdaGrad++ and Adam++ without predefined learning rates and proved their convergence.
result AdaGrad++ and Adam++ achieve comparable convergence rates to AdaGrad and Adam respectively.

D-Adaptation automatically sets optimal learning rates without manual tuning.

problem Optimizing learning rates for efficient convergence in machine learning.
method D-Adaptation, which asymptotically achieves optimal learning rates without back-tracking or additional evaluations.
result D-Adaptation automatically matches hand-tuned learning rates across diverse problems.

New algorithms learn latent variable models without tuning, outperforming existing methods.

problem Learning latent variable models without manual tuning.
method Two particle-based algorithms using free energy minimization and coin betting.
result Learning algorithms are entirely tuning-free and competitive with existing methods.

We define risk-free portfolios using three gauge invariant differential operators that require such portfolios to be insensitive to price changes, to be self-financing, and to produce a zero real return so there are no risk-free profits. This definition identifies the risk-free rate as the return of an infinitely diver…

2016-05-11abs ↗pdf ↗

Develops a parameter-free SGD algorithm with optimal convergence rate.

problem Optimizing parameters in stochastic convex optimization.
method A novel parameter-free algorithm for SGD with high-probability guarantees and adaptive properties.
result Achieves optimal convergence rate with only a double-logarithmic factor increase compared to known-parameter settings.

Characterizes distribution-free rates in unbalanced classification problems.

problem Minimizing error under two different distributions in unbalanced settings.
method Characterizes minimax rates over all pairs of distributions using a geometric condition.
result Identifies a dichotomy between hard and easy classes based on a three-points-separation condition.

New Hessian-free method improves bilevel optimization for meta-learning.

problem Efficiently solving bilevel optimization problems with limited second-order information.
method Proposes a new Hessian-free method that approximates the response Jacobian matrix via optimization path differences.
result Demonstrates superior performance on meta-learning tasks compared to baseline methods.

Model for corporate bond pricing with credit rating migration, solving a double free boundary problem.

problem Corporate bond pricing with credit rating migration risks.
method Established a pricing model as a double free boundary problem, proving existence, uniqueness, and regularity of the solution.
result Two free boundaries are shown to be smooth and converge to a traveling wave solution as time goes to infinity.

The study introduces anytime learning schedules for large language models without fixed horizons.

problem Training large language models without knowing the total training horizon.
method Theoretical analysis and weight averaging to create anytime learning schedules.
result Theoretical and empirical evidence shows that weight averaging with simple step sizes can achieve comparable final loss to well-tuned cosine schedules.

New algorithm reduces adaptation lag in online model selection.

problem Adaptation lag in online model selection for non-stationary environments.
method Optimistic online mirror descent with safeguarded large learning rates.
result Reduces adaptation lag from hundreds of rounds to a few rounds.

We provided an analytical representation of the price of a barrier option with one type of special moving barrier. We consider the case that risk free rate, dividend rate and stock volatility are time dependent. We get a pricing formula and put call parity for barrier option when the moving barrier has a special relati…

2013-03-06abs ↗pdf ↗

New algorithms for sampling in constrained domains without learning rates.

problem Sampling in constrained domains with fairness constraints and post-selection inference.
method Coin betting ideas from convex optimisation and a unifying framework for constrained sampling.
result Our algorithms achieve competitive performance without hyperparameter tuning.

Paper analyzes Hit-and-Run's convergence rates and applies similar methods to randomized Kaczmarz.

problem Quantifying advantages of Hit-and-Run's coordinate-free property.
method Sharp estimates via coupling methods and mixing time bounds.
result Ballistic and superdiffusive convergence rates in certain settings.

The paper studies estimation of parameters of diffusion market models from historical data. The standard definition of implied volatility for these models presents its value as an implicit function of several parameters, including the risk-free interest rate. In reality, the risk free interest rate is unknown and need …

2013-03-20abs ↗pdf ↗

New learning dynamics achieve fast convergence in games without needing to know utility scales.

problem Fast convergence guarantees in learning games require prior knowledge of utility scales.
method Developed scale-free and scale-invariant learning dynamics using optimistic follow-the-regularized-leader with adaptive learning rates and clipping techniques.
result Achieved fast convergence rates to Nash and correlated equilibria without prior utility scale knowledge.

A method for making predictions with a reject option using conformal prediction.

problem Uncertainty in machine learning predictions, especially when models are unsure.
method Formalizing ML with reject option, using conformal prediction for distribution-free error guarantees.
result Theoretical guarantees on error rate for prediction sets with distribution-free validity.

Deep learning framework for bond and yield curve forecasting with no-arbitrage constraints.

problem Arbitrage-free yield curve and bond price forecasting.
method Combines Kalman, extended Kalman, and particle filters with LSTM/CLSTM, and introduces AER term.
result Arbitrage regularization improves forecast accuracy, especially at short maturities.

This paper shows that a perturbed form of gradient descent converges to a second-order stationary point in a number iterations which depends only poly-logarithmically on dimension (i.e., it is almost "dimension-free"). The convergence rate of this procedure matches the well-known convergence rate of gradient descent to…

2017-03-02abs ↗pdf ↗

Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks. …

2017-05-22abs ↗pdf ↗

We develop an algorithm for minimizing a function using nn batched function value measurements at each of TT rounds by using classifiers to identify a function's sublevel set. We show that sufficiently accurate classifiers can achieve linear convergence rates, and show that the convergence rate is tied to the difficu…

2018-04-11abs ↗pdf ↗

This study shows how monetary uncertainty affects stock market reactions to macroeconomic news.

problem Understanding stock market reactions to macroeconomic news under varying levels of monetary uncertainty.
method Decomposes stock market response into cash flow and risk-free rate channels, analyzing time-varying effects.
result High monetary uncertainty weakens the positive stock market response to macroeconomic news.

New algorithms for multivariate RL improve decision-making in complex systems.

problem Complex multi-objective decision-making in reinforcement learning.
method Oracle-free and computationally-tractable algorithms for multivariate distributional RL.
result Convergence rates match scalar reward settings and provide insights into reward dimensionality.

We decode latent states in Block MDPs and learn near-optimal policies.

problem Model estimation and reward-free learning in Block MDPs.
method Information-theoretical lower bound and efficient model estimation algorithm.
result Our algorithm approaches the information-theoretical limit for latent state decoding and converges to optimal policies.

It is assumed that under suitable economic and information-theoretic conditions, market exchange rates are free from arbitrage. Commodity markets in which trades occur over a complete graph are shown to be trivial. We therefore examine the vector space of no-arbitrage exchange rate ensembles over an arbitrary connected…

2014-06-05abs ↗pdf ↗

WSqD extends learning rate schedules for large model training without fixed horizons.

problem Fixed learning rate schedules limit training horizon extension.
method WSqD replaces constant stable phase with a shifted inverse-square-root base, retaining linear cooldown.
result WSqD achieves minimax-optimal convergence rate and horizon-independence.

Adaptive learning rates improve FTPL's BOBW guarantees in bandit problems.

problem Improving Follow-the-Perturbed-Leader's BOBW guarantees in bandit problems.
method Introducing surrogate probability functions to compute adaptive learning rates without exact probabilities.
result BOBW guarantees for FTPL with Pareto perturbations for any α>1α>1.

Optimal buying and selling times for homes in fluctuating interest rates.

problem Maximizing profit from buying and selling homes in a market with variable interest rates.
method Nested optimal stopping problem solved using a nonnegative concave majorant approach.
result Investor's optimal buying and selling strategies derived for CIR interest rates.