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.

168,742 papers · 148 categories

Trend · papers per month

20406080 · May 202619922001200920172026
48 results for downstream instability

The paper explores how word embeddings affect the stability of downstream NLP models.

problem Small changes in training data can cause significant changes in model predictions.
method Empirical and theoretical analysis of embedding instability, including the introduction of eigenspace instability measure.
result Increasing embedding memory can reduce the disagreement in predictions by 5% to 37%.

Improved RL training for DMs reduces mode collapse and preserves diversity.

problem Mode collapse and training instability in RL fine-tuned diffusion models.
method Dynamic hierarchical RL training with sliding-window parameter regularisation.
result Models trained with HRF achieve better preservation of diversity in downstream tasks.

Generative models often fail to preserve joint structure despite matching marginals.

problem Generative models fail to capture complex dependencies beyond univariate marginals.
method Introduced D_Sigma(P,Q) = ||Sigma_P - Sigma_Q||_F to measure covariance-level dependence fidelity.
result Covariance-level divergence can lead to structural instability in downstream inference.

BERT fine-tuning is unstable due to optimization issues, not forgetting or dataset size.

problem Stability of fine-tuning BERT-based models across different random seeds.
method Analysis of BERT, RoBERTa, and ALBERT fine-tuned on GLUE datasets, identifying optimization difficulties as the cause of instability.
result Fine-tuning instability is due to optimization difficulties leading to vanishing gradients, not forgetting or dataset size.

New method stabilizes machine learning predictions across random seeds.

problem Machine learning predictions vary across random seeds, causing instability.
method Introduces adaptive cross-bagging to eliminate seed dependence.
result Adaptive cross-bagging achieves targeted stability in debiased machine learning.

We improve current instability-based methods for the selection of the number of clusters kk in cluster analysis by developing a normalized cluster instability measure that corrects for the distribution of cluster sizes, a previously unaccounted driver of cluster instability. We show that our normalized instability mea…

2016-08-26abs ↗pdf ↗

We identify spectral conditions for reliable neural probe interpretation.

problem Unreliable performance of linear probes in interpreting neural representations.
method Formalized Spectral Identifiability Principle (SIP) based on eigengap and Fisher error.
result Reliability of neural probes depends on the eigengap relative to Fisher estimation error.

Some exotic compact objects possess evanescent ergosurfaces: timelike submanifolds on which a Killing vector field, which is timelike everywhere else, becomes null. We show that any manifold possessing an evanescent ergosurface but no event horizon exhibits a linear instability of a peculiar kind: either there are solu…

2018-10-06abs ↗pdf ↗

Interval Neural Networks detect instabilities in image reconstructions.

problem Detecting instabilities in deep learning image reconstructions.
method Employed uncertainty quantification methods with Interval Neural Networks.
result Interval Neural Networks effectively reveal image reconstruction instabilities.

Note on instabilities in super-time-stepping methods for Heston model.

problem Instabilities in super-time-stepping methods applied to Heston model.
method Exploration of explicit super-time-stepping schemes (RK-Chebyshev, RK-Legendre) for Heston model.
result Relevance of stability remarks beyond super-time-stepping schemes.

Binary perceptron's instability linked to replica symmetry breaking.

problem Understanding the relationship between algorithmic instability and replica symmetry breaking in binary perceptron learning.
method Established the connection between algorithmic instability and replica symmetry breaking by comparing the instability condition around the fixed point to the instability for breaking the replica symmetric solution of the free energy function.
result The instability condition around the algorithmic fixed point is identical to the instability for breaking the replica symmetric saddle point solution of the free energy function.

The study examines stability and instability of Poincaré-Einstein metrics using Ricci flow.

problem Stability and instability of Poincaré-Einstein metrics.
method Variant of expander entropy for asymptotically hyperbolic manifolds, local positive mass theorem, volume comparison.
result Characterization of stability and instability in terms of local positive mass theorem and volume comparison.

POTNet uses penalized optimal transport to generate data without mode collapse.

problem Mode collapse in WGANs leading to poor synthetic data generation.
method POTNet employs marginally-penalized Wasserstein distance for deep generative modeling.
result POTNet effectively captures underlying data structures, including tail behaviors and minor modalities.

Study shows instability of naked singularities in perfect fluid models.

problem Instability of naked singularities in Einstein equations coupled with isothermal perfect fluid.
method Investigated spherically symmetric self-similar naked singularities under C1,αC^{1,α} perturbations of an external massless scalar field.
result Spherically symmetric self-similar naked singularities are unstable to trapped surface formation.

Clinical models can be unstable, leading to unreliable predictions.

problem Stability of clinical prediction models developed using statistical or machine learning methods.
method Simulation and case studies of statistical and machine learning approaches to show instability in model predictions.
result Model instability often leads to miscalibration of predictions in new data.

A data-driven approach predicts morphological development under structural instability.

problem Understanding and predicting spatiotemporal complexities of morphogenesis under structural instability.
method Machine-learning framework based on physical modeling of morphogenesis.
result Identification of key bifurcation characteristics and prediction of history-dependent development.

Study shows instability of naked singularities in scalar field models.

problem Stability of naked singularities in spherically symmetric Einstein-Scalar field systems.
method Analysis of a family of incoming null cones becoming increasingly singular.
result Naked singularities are unstable to black hole formation under certain perturbations.

The paper studies stability and instability of minimal submanifolds in complex Einstein spaces.

problem Stability and instability of minimal submanifolds in complex Einstein spaces.
method Computation of index and nullity, investigation of stability, and algorithm for higher eigenvalues.
result Criterion for instability of minimal submanifolds in some cases.

The study examines the stability of Einstein metrics on Sasaki Einstein and nearly parallel G2 manifolds.

problem Linear instability of Einstein metrics on Sasaki Einstein and nearly parallel G2 manifolds.
method Analysis of the second and third Betti numbers for Sasaki Einstein and nearly parallel G2 manifolds.
result Positive second and third Betti numbers lead to linear instability for the respective manifolds.

Paper extends Simons theorem to FF-Yang-Mills connections for instability.

problem Tackles instability of FF-Yang-Mills connections.
method Extends Simons theorem to FF-Yang-Mills connections using Kobayashi-Ohnita-Takeuchi's method.
result Derives a sufficient condition for instability of non-flat FF-Yang-Mills connections.

Proposes a new measure to evaluate stability of statistical parameters under distributional shifts.

problem Difficulty in transferring knowledge across data sets due to distributional changes.
method Introduces a measure of instability quantifying sensitivity of statistical parameters to Kullback-Leibler divergence and directional shifts.
result The proposed measure can elucidate the type of shifts a parameter is sensitive to and improve estimation accuracy under shifted distributions.

The paper analyzes numerical instability in variational flows and proposes a diagnostic method.

problem Numerical instability in variational flows affects sampling, density evaluation, and ELBO estimation.
method Treated variational flows as dynamical systems, used shadowing theory for theoretical guarantees, and developed a diagnostic procedure.
result Despite numerical instability, results from variational flows can be accurate enough for practical applications.

Proposes a continuous flow model to understand and control instability in gradient descent for deep learning.

problem Understanding and controlling the instability of gradient descent in deep learning.
method Introduces the Principal Flow (PF), a continuous time flow that approximates gradient descent dynamics.
result The PF captures divergent and oscillatory behaviors of gradient descent, including escaping local minima and saddle points.

Study on instability of extreme Reissner-Nordström spacetime perturbations.

problem Linear stability of gravitational and electromagnetic perturbations in extreme Reissner-Nordström spacetime.
method Extends Giorgi's framework to prove instability results for a set of gauge invariant quantities along the event horizon.
result Proves decay, non-decay, and polynomial blow-up estimates for certain quantities along the event horizon, depending on the number of derivatives.

Theoretical analysis shows pretext-based self-supervised learning can be boosted by downstream data under certain conditions.

problem Theoretical analysis of pretext-based self-supervised learning and downstream data refinement.
method Theoretical analysis and experiments on synthetic and real-world datasets.
result Theoretical lower bounds and experiments show that downstream data refinement can boost or hurt performance depending on conditions.

This study examines how the size and alignment of pretraining data affect the performance of large language models on downstream tasks.

problem Understanding how the size and alignment of pretraining data impact the performance of large language models on downstream tasks.
method Investigated the scaling behavior of large language models in a transfer learning setting, focusing on machine translation tasks.
result The size of the finetuning dataset and the distribution alignment between pretraining and downstream data significantly influence the scaling behavior of downstream performance.

Dual-objective GANs reduce training instabilities with tunable α-loss parameters.

problem Training instabilities in Generative Adversarial Networks (GANs).
method Introduce (αD,αG)(α_D,α_G)-GANs with dual objectives modeled using αα-loss.
result Upper bounds on estimation error show improved performance under certain conditions.

Study uses DNM theory to detect early warning signals of market instability.

problem Detecting early warning signals of financial market instability.
method Applying Dynamical Network Marker (DNM) theory to trading data from the Tokyo Stock Exchange.
result Early warning signals of large price movements can be detected on a daily time scale.

We prove the instability of some families of Riemannian manifolds with non-trivial real Killing spinors. These include the invariant Einstein metrics on the Aloff-Wallach spaces Nk,l=SU(3)/ik,l(S1)N_{k, l}={\rm SU}(3)/i_{k, l}(S^{1}) (which are all nearly G2{\rm G}_2 except N1,0N_{1,0}), and Sasaki Einstein circle bundles over certain ir…

2018-10-10abs ↗pdf ↗

Following the financial crisis of 2007-2008, a deep analogy between the origins of instability in financial systems and complex ecosystems has been pointed out: in both cases, topological features of network structures influence how easily distress can spread within the system. However, in financial network models, the…

2016-02-18abs ↗pdf ↗

Paper defines and solves a problem in representation learning to ensure fairness with high confidence.

problem Learning fair representations with high confidence guarantees for all downstream tasks.
method Formally defines the problem, introduces FRG framework, proves high probability fairness, and demonstrates effectiveness empirically.
result FRG framework provides high-confidence guarantees for limiting unfairness across all downstream models and tasks.

Study shows how pretraining robustness transfers to downstream tasks.

problem Understanding how robustness is transferred from pretraining to downstream tasks.
method Theoretical analysis and practical validation of robustness constraints.
result Robustness of a linear predictor on downstream tasks can be constrained by the robustness of its underlying representation.

Graph auto-encoders predict stock market instability by measuring graph structure changes.

problem Forecasting stock market instability and volatility.
method Use graph auto-encoders to reconstruct graph structure and measure changes.
result Higher GAE reconstruction error correlates with higher volatility.

Self-supervised metric learning boosts downstream tasks in multi-view data.

problem Improving distance-based downstream tasks without labeled data.
method Developed a statistical framework to study self-supervised metric learning in multi-view data.
result Self-supervised metric learning improves target distances for various downstream tasks.