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

3467101134 · May 202619922001200920172026
48 results for Training-Evaluation Gap

Unified approach optimizes neural network training for various metrics.

problem Training and evaluation of neural network binary classifiers often use different metrics.
method Combines differentiable approximation and probabilistic soft sets.
result Effective in optimizing for metrics like F1-Score across various domains.

This work interprets diffusion score matching using normalizing flows for better model training and evaluations.

problem Limitations of diffusion score matching when dealing with certain types of distributions.
method The approach involves interpreting the diffusion matrix using normalizing flows to provide better interpretation and usage of diffusion score matching.
result Diffusion score matching is equivalent to the original score matching evaluated in the transformed space defined by the normalizing flow.

PLUMAGE improves large model training efficiency and stability.

problem Accelerator memory and networking constraints during large model training.
method Probabilistic Low rank Unbiased Minimum Variance Gradient Estimator (PLUMAGE) that resolves bias and variance issues.
result PLUMAGE reduces training loss by 28% on average across the GLUE benchmark.

Paper explores how generative models can be made more creative.

problem Limitation of generative models in diverging from original data distribution.
method Proposes a novel training objective called Bounded Adversarial Divergence (BAD) to enable creative divergence.
result Preliminary results suggest BAD can enable creative divergence in generative models.

Deep learning models struggle with new data in stock price trend prediction.

problem Stock price trend prediction using Deep Learning models.
method Examination of fifteen state-of-the-art DL models on LOB data, using LOBCAST framework.
result All models show significant performance drop with new data, questioning their market applicability.

This paper introduces Selective-Backprop, a technique that accelerates the training of deep neural networks (DNNs) by prioritizing examples with high loss at each iteration. Selective-Backprop uses the output of a training example's forward pass to decide whether to use that example to compute gradients and update para…

2019-10-02abs ↗pdf ↗

New method reduces discrete flow transitions, improving perplexity estimation.

problem Stochasticity in discrete paths makes rectification strategies ineffective.
method Dynamic-optimal-transport-like minimization objective with minibatch strategies.
result 32 times reduction in transitions for same perplexity.

Current reading comprehension models generalise well to in-distribution test sets, yet perform poorly on adversarially selected inputs. Most prior work on adversarial inputs studies oversensitivity: semantically invariant text perturbations that cause a model's prediction to change when it should not. In this work we f…

2020-02-15abs ↗pdf ↗

In the real world, a learning system could receive an input that is unlike anything it has seen during training. Unfortunately, out-of-distribution samples can lead to unpredictable behaviour. We need to know whether any given input belongs to the population distribution of the training/evaluation data to prevent unpre…

2018-09-13abs ↗pdf ↗

Unified scoring model improves efficiency and performance across multiple tasks.

problem Efficient and resource-efficient automated scoring for diverse tasks.
method Knowledge-distilled multi-task Mixture-of-Experts (MoE) approach.
result Comparable performance to task-specific models with significantly less storage and training resources.

Emergent misalignment is influenced by training dynamics, model priors, and data.

problem Emergent misalignment in models
method Exploring training dynamics, model priors, and data
result Activation deltas before and after narrow fine-tuning correlate with their similarities when measured with the last prompt-token activations.

The article proves a conjecture about the fundamental gap for horoconvex domains in hyperbolic space.

problem Proving a conjecture about the fundamental gap for horoconvex domains in hyperbolic space.
method Establishing conformal log-concavity estimates for the first eigenfunction.
result Proves a conjecture about the fundamental gap for horoconvex domains in hyperbolic space.

Study shows gaps in Bitcoin order book are linked to returns but only in the short term.

problem Understanding the relationship between gaps and returns in Bitcoin order books.
method Examined the dynamics of gaps and returns in a Bitcoin order book without considering long-term causation.
result The causal relationship between gaps and returns is limited to instantaneous causation.

Researchers compute gap distributions for saddle connection directions on specific translation surfaces.

problem Computing gap distributions for saddle connection directions on translation surfaces.
method Translation to dynamical question of return times to a transversal under the horocycle flow.
result Gap distributions have support at 0 and quadratic tail decay.

The paper introduces gapped scale-sensitive dimensions to improve learning rate bounds.

problem Improving lower bounds on rates of convergence in statistical and online learning.
method Introducing and analyzing gapped scale-sensitive dimensions for function classes.
result Gapped dimensions lead to stronger lower bounds on offset Rademacher averages.

The article explores the fundamental gap in Bakry-Emery geometry.

problem The fundamental gap in Bakry-Emery geometry.
method Recalled Bakry-Emery geometry and connected eigenvalues with boundary conditions. Showed a connection between fundamental gap and Bakry-Emery geometry.
result Presented key ideas in Andrews's and Clutterbuck's proof of the fundamental gap conjecture.

The paper calculates gap distributions for translation surfaces, focusing on the double heptagon.

problem Calculating gap distributions for translation surfaces.
method Describes a procedure to find winning holonomy vectors and applies it to the double heptagon.
result Explicitly computed gap distribution for the regular double heptagon translation surface.

Improved gap-dependent bounds for reinforcement learning with linear approximations.

problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.

We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrain…

2018-07-13abs ↗pdf ↗

Computing unlinking number is usually very difficult and complex problem, therefore we define BJ-unlinking number and recall Bernhard-Jablan conjecture stating that the classical unknotting/unlinking number is equal to the BJ-unlinking number. We compute BJ-unlinking number for various families of knots and links for w…

2005-03-14abs ↗pdf ↗

New methods reduce bias in estimating optimality gaps for risk-averse stochastic programs.

problem Optimality gap estimation bias in risk-averse stochastic programs.
method Two independent samples, each estimating a different component of the optimality gap.
result Our method reduces bias in estimating optimality gaps for risk-averse problems.

Federated learning studies separate client data and distribution gaps.

problem Understanding performance differences in federated learning across different datasets.
method Proposed a framework to disentangle out-of-sample and participation gaps.
result Dataset synthesis strategy is crucial for realistic simulations of federated learning generalization.

The paper proves gap theorems for Yang-Mills on manifolds with positive Yamabe.

problem Yang-Mills theory on manifolds with positive Yamabe constant.
method Extending Gursky-Kelleher-Streets results to complete manifolds.
result Equality in gap theorem described in terms of basic instanton.

Study shows fundamental gap of horoconvex domains in hyperbolic space has no positive lower bound.

problem Understanding the fundamental gap of horoconvex domains in hyperbolic space.
method Analysis of fundamental gap of geodesic balls as radius goes to infinity.
result Product of fundamental gap and square of diameter has no positive lower bound for horoconvex domains.

Study spectral gaps in hyperbolic rational homology spheres.

problem Finding spectral gaps in hyperbolic rational homology spheres.
method Construction of families of hyperbolic rational homology spheres with coexact 1-form spectral gaps.
result Provided intervals containing limit points of spectral gaps, with the rightmost interval being [0.8196, 0.8277].

New convex domains in hyperbolic space can have lower fundamental gap than constant potentials.

problem Finding convex domains with lower fundamental gap than constant potentials.
method Constructing specific convex domains and potentials with controlled eigenfunctions.
result Fundamental gap of Δ+V-Δ+V can be strictly smaller than Δ for convex domains.

The paper establishes pressure gaps for manifolds with flat subtori singularities.

problem Understanding phase transitions in nonpositively curved manifolds with flat subtori.
method Derives a pressure gap criterion for closed rank 1 manifolds with specific singular sets and proves Hölder continuity of geometric potentials.
result Geometric potentials have pressure gaps and no phase transitions under certain curvature constraints.

In their celebrated work, B. Andrews and J. Clutterbuck proved the fundamental gap (the difference between the first two eigenvalues) conjecture for convex domains in the Euclidean space and conjectured similar results holds for spaces with constant sectional curvature. We prove the conjecture for the sphere. Namely wh…

2016-06-03abs ↗pdf ↗