The muti-layer information bottleneck (IB) problem, where information is propagated (or successively refined) from layer to layer, is considered. Based on information forwarded by the preceding layer, each stage of the network is required to preserve a certain level of relevance with regards to a specific hidden variab…
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
48 results for “successive refinement”
A new algorithm selects models for contextual bandits, reducing regret.
problem Model selection for stochastic contextual bandits under realizability assumption.
method Adaptive Contextual Bandit (ACB) algorithm, successive refinement phases.
result ACB algorithm achieves similar regret bound to known algorithms, with a model selection cost.
IterefinE combines KG refinement with embeddings to improve KG quality.
problem Noisy Knowledge Graphs lead to poor performance in downstream tasks.
method Iterative KG refinement using embeddings and inference rules.
result Improved KG refinement leading to higher F1 scores.
This work improves data reconstruction methods by ensuring unique solutions and refining optimization.
problem Ensuring unique solutions and optimizing reconstruction from KKT conditions.
method Discussion of sufficient conditions for unique solutions and introduction of sample splitting for optimization.
result Sample splitting improves reconstruction performance across various methods.
We consider the problem of learning from sparse and underspecified rewards, where an agent receives a complex input, such as a natural language instruction, and needs to generate a complex response, such as an action sequence, while only receiving binary success-failure feedback. Such success-failure rewards are often …
Holomorphic quantum modular forms linked to knot volumes.
problem Understanding algebraic properties of quantum modular forms.
method Analyzing descendant state integrals for specific knots.
result Illustrated algebraic properties for the (-2,3,7)-pretzel knot.
Improved neural image compression with refined latent representations.
problem Sub-optimal results from variational autoencoders due to imperfect optimization and capacity limitations.
method Stochastic Gumbel Annealing (SGA) and its extensions (SGA+), including three different methods.
result Significant improvement in compression performance, especially on the R-D trade-off.
For each sequence of polynomials, P=(p_1(t),p_2(t),...), we define a characteristic series of groups, called the derived series localized at P. Given a knot K in S^3, such a sequence of polynomials arises naturally as the orders of certain submodules of the sequence of higher-order Alexander modules of K. These group s…
TREK uses distillation to help students solve hard problems.
problem Stalled progress on hard prompts when current policy lacks useful reasoning trajectories.
method TREK combines distillation and reinforcement learning to expand student support.
result TREK significantly improves student performance on mathematical reasoning and agentic tasks.
Meta-learning has emerged as an important framework for learning new tasks from just a few examples. The success of any meta-learning model depends on (i) its fast adaptation to new tasks, as well as (ii) having a shared representation across similar tasks. Here we extend the model-agnostic meta-learning (MAML) framewo…
Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer design, however, only considers pairs of information objects, making it unsuitable for problems requiring reasoning across a higher number of fa…
This work refines Cover's theory for binary classification on low-dimensional data.
problem The challenge of analyzing how low-dimensional data structures affect classification models.
method Refines Cover's function-counting theory to account for low-dimensional data structure.
result Derives dichotomy counts and analyzes the impact of data structure on classification models.
Improved compressed sensing using a generator that learns from measurements.
problem Signal recovery accuracy in compressed sensing.
method Proposes a framework that uses measurement-conditional generative models to refine signal estimation.
result Uniformly superior performance with up to an order of magnitude reduction in reconstruction error.
Improved algorithm for clustered Federated Learning reduces initialization and hyperparameter requirements.
problem Dichotomy between heterogeneous models and simultaneous training in Federated Learning.
method Proposes a new clustering framework and an improved algorithm ( exttt{SR-FCA}) that removes restrictive assumptions.
result Improves clustering accuracy and removes the need for good initialization and hyperparameters.
Study examines volatility-based strategy for Chinese ETF options, improving returns in volatile markets.
problem Lack of effective trading strategies in volatile Chinese equity markets.
method Volatility forecasting using GARCH models to dynamically adjust positions and exposures.
result Dynamic adjustment of positions and exposures enhances returns in volatile markets.
New findings show margins are not sufficient for explaining gradient boosting performance.
problem The inadequacy of margin explanations in explaining the performance of gradient boosting.
method Demonstrated and proved a stronger margin-based generalization bound for boosted classifiers.
result Proved a stronger margin-based generalization bound that explains the performance of modern gradient boosters.
Molecule optimization is about generating molecule with more desirable properties based on an input molecule . The state-of-the-art approaches partition the molecules into a large set of substructures and grow the new molecule structure by iteratively predicting which substructure from to add. However, s…
Substantial progress has been made recently on developing provably accurate and efficient algorithms for low-rank matrix factorization via nonconvex optimization. While conventional wisdom often takes a dim view of nonconvex optimization algorithms due to their susceptibility to spurious local minima, simple iterative …
Algorithm recovers causal graphs in presence of latent confounders and selection bias.
problem Recovering causal graphs in the presence of latent confounders and selection bias.
method Iterative causal discovery (ICD) algorithm that relies on causal Markov and faithfulness assumptions.
result Sound and complete algorithm that recovers the equivalence class of the underlying causal graph.
Algorithm recovers causal graphs from data with fewer tests.
problem Recovering causal graphs from observational data with latent confounders and selection bias.
method Iterative CI tests with increasing condition set sizes.
result Significantly fewer CI tests and condition sets compared to FCI.
New inequality for refined knot invariants in a specific space.
problem General adjunction inequality for refined -invariants does not hold.
method Introduced an adjunction inequality for a specific spatial refinement in .
result An adjunction inequality holds for the -version of the -refinement in .
This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from…
We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between so…
We study refined topological string theory in the presence of orientifolds by counting second-quantized BPS states in M-theory. This leads us to propose a new integrality condition for both refined and unrefined topological strings when orientifolds are present. We define the SO(2N) refined Chern-Simons theory which co…
Study reveals differences in medical image models' hidden representation refinement.
problem Understanding how intrinsic dimensionality changes in neural network hidden representations across different domains.
method Analysis of 11 natural and medical image datasets using 6 network architectures.
result Medical image models refine hidden representations earlier, suggesting differences in feature abstraction.
Refines neural network predictions using background knowledge for improved accuracy.
problem Compensate for lack of labeled data in neural networks.
method Introduces differentiable refinement functions and Iterative Local Refinement (ILR) algorithm to refine predictions efficiently and accurately.
result ILR finds competitive results in MNIST addition task and refines predictions on complex SAT formulas.
New research shows label refinement and weak training have limitations for aligning LLMs.
problem Limitations of refinement methods for aligning large language models.
method Analyzed probabilistic assumptions and alternative approaches to label refinement and weak training.
result Label refinement and weak training suffer from irreducible error, leaving a performance gap.
Remasking improves the quality of discrete diffusion models for natural language and image generation.
problem Limited iterative refinement in masked discrete diffusion models.
method Introducing ReMDM sampler that allows remasking during inference.
result Remasking enables better quality outputs with increased sampling steps.
While neural sequence generation models achieve initial success for many NLP applications, the canonical decoding procedure with left-to-right generation order (i.e., autoregressive) in one-pass can not reflect the true nature of human revising a sentence to obtain a refined result. In this work, we propose XL-Editor, …
We refine Khovanov homology in the presence of an involution on the link. This refinement takes the form of a triply-graded theory, arising from a pair of filtrations. We focus primarily on strongly invertible knots and show, for instance, that this refinement is able to detect mutation.
The paper develops a theory for identifying the best arm in non-parametric multi-armed bandits with a fixed budget.
problem Identifying the best arm in non-parametric multi-armed bandits with a limited number of trials.
method The paper proposes upper and lower bounds on the average log-probability of misidentification using information-theoretic quantities and a refined analysis of the successive-rejects strategy.
result The paper provides new upper and lower bounds on the average log-probability of misidentification, which generalize existing bounds.
In a previous paper we constructed a spectrum-level refinement of Khovanov homology. This refinement induces stable cohomology operations on Khovanov homology. In this paper we show that these cohomology operations commute with cobordism maps on Khovanov homology. As a consequence we obtain a refinement of Rasmussen's …
Refined 3D indexhep-th
Refined 3D index uses surgery and gradings to distinguish 3-manifolds.
problem Distinguishing 3-manifolds and gauge theories phases.
method Dehn surgery presentation, ideal triangulation, and enhanced flavor symmetries.
result Invariance of refined index under various transformations.
Refines deep generative models to improve data density precision.
problem Achieving precise representation of data probability density in deep models.
method Iterated generative modeling to refine latent space, addressing topological obstructions.
result Latent Space Refinement (LaSeR) protocol improves generative model precision.
Bauer-Furuta invariantsmath.DG
Established a stable cohomotopy refinement for Pin(2) monopole invariants.
problem Refining monopole invariants for Pin(2) structures.
method Adapted Bauer-Furuta's Seiberg-Witten refinement method to Pin(2) monopole invariants.
result Connected sum formula for the refined invariants.
ConfHit provides valid guarantees for generative models without oracle access.
problem Reliable guarantees for novel candidate generation in generative models.
method Formalizes certification and refinement of generated sets, leveraging weighted exchangeability and density-ratio weighted conformal p-values.
result Consistently delivers valid coverage guarantees and compact certified sets across various generative tasks.
Deep networks improve by progressively refining approximations at each layer.
problem Standard approximation theory doesn't explain the role of intermediate layers in deep neural networks.
method Developed a mixed-activation architecture with a geometric scale interpretation of depth.
result Each intermediate layer approximates the target function with a geometric rate.
Refined 1-cocycle for knots helps quantify isotopies.
problem Quantify knot isotopies using refined tangle equations.
method Refined combinatorial 1-cocycle for regular isotopies of knots.
result Refined tangle equations provide quantitative knot information.
Self-training improves model accuracy by refining pseudo-labels.
problem Improving semi-supervised learning with self-training.
method Theoretical insights into self-training algorithm with a focus on linear classifiers.
result Self-training iterations can improve model accuracy even if stuck in sub-optimal fixed points.
Braverman and Kappeler introduced a refinement of the Ray-Singer analytic torsion associated to a flat vector bundle over a closed odd-dimensional manifold. We study this notion and improve the Braverman-Kappeler theorem comparing the refined analytic torsion with Farber-Turaev refinement of the combinatorial torsion. …
We note that our stable homotopy refinements of Khovanov's arc algebras and tangle invariants induce refinements of Chen-Khovanov and Stroppel's platform algebras and tangle invariants, and discuss the topological Hochschild homology of these refinements.
EGR refines and assesses protein complex structures.
problem Improving the accuracy of protein complex 3D structures for drug discovery.
method E(3)-equivariant graph neural network (GNN) for multi-task refinement and assessment.
result EGR achieves state-of-the-art performance in refining and assessing protein complexes.
A novel framework refines diffusion models iteratively for better downstream reward optimization.
problem Optimizing reward functions during inference of diffusion models.
method Iterative refinement process with noising and reward-guided denoising steps.
result Superior empirical performance in protein and DNA design.
We formulate large duality of refined Chern-Simons theory with a torus knot/link in . By studying refined BPS states in M-theory, we provide the explicit form of low-energy effective actions of Type IIA string theory with D4-branes on the -background. This form enables us to relate refined C…
Study uses AI to refine loan assessments, improving credit default predictions.
problem Improving credit default prediction accuracy using AI-refined text.
method Comparative analysis of human-written and AI-refined loan assessments using deep learning techniques.
result AI-refined texts significantly enhance credit default predictions, especially when combined with structured data.
Let be a flat complex vector bundle over a closed oriented odd dimensional manifold endowed with a flat connection . The refined analytic torsion for was defined and studied by Braverman and Kappeler. Recently Mathai and Wu defined and studied the analytic torsion for the twisted de Rham complex…
The refined analytic torsion, defined by M. Braverman and T. Kappeler on closed manifolds, can be viewed as a refinement of the Ray-Singer torsion, since it is a canonical choice of an element with Ray-Singer norm one, in case of unitary representations. The complex phase of the refinement is given by the rho-invariant…
Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL). State-of-the-art RL algorithms suffer from high sample complexity, particularly in the sparse reward case, where they can do no better than to explore in all directions until the first positive rewards are found. To mitigate …