Negative / Null Result ReportOpen accessComputer Science
A. Donini, E. Fernandez-Martinez, S. Rigolin · 2004 · arXiv
In this letter we present the study of the eightfold degeneracy in the $(θ_{13},δ)$ measurement including both appearance and disappearance channels. We analyse, for definiteness, the case of a standard low-$γ$ $β$-Beam and a 4 MWatt SPL Super-Beam facility, both aiming at a UNO-like Mton water Cerenkov detector located at the Frejus laboratory, $L = 130$ km. In the $β$-Beam case, the \nue disappearance channel does not improve the $(θ_{13},δ)$ measurement when a realistic (i.e. $\ge$ 2%) systematic error is included. In the Super-Beam case, the \numu disappearance channel could, instead, be q
Negative / Null Result ReportOpen accessComputer Science
Chen Cai, Yusu Wang · 2020 · arXiv
Graph Neural Networks (GNNs) have achieved a lot of success on graph-structured data. However, it is observed that the performance of graph neural networks does not improve as the number of layers increases. This effect, known as over-smoothing, has been analyzed mostly in linear cases. In this paper, we build upon previous results \cite{oono2019graph} to further analyze the over-smoothing effect in the general graph neural network architecture. We show when the weight matrix satisfies the conditions determined by the spectrum of augmented normalized Laplacian, the Dirichlet energy of embeddin
Negative / Null Result ReportOpen accessComputer Science
Charles Welch, Rada Mihalcea, Jonathan K. Kummerfeld · 2020 · arXiv
Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation o
Negative / Null Result ReportOpen accessComputer Science
Dhananjay Srivastava · 2023 · arXiv
Clinical conversation summarization has become an important application of Natural language Processing. In this work, we intend to analyze summarization model ensembling approaches, that can be utilized to improve the overall accuracy of the generated medical report called chart note. The work starts with a single summarization model creating the baseline. Then leads to an ensemble of summarization models trained on a separate section of the chart note. This leads to the final approach of passing the generated results to another summarization model in a multi-layer/stage fashion for better coh
Negative / Null Result ReportOpen accessComputer Science
Roy Abel, Idan Benami, Yoram Louzoun · 2019 · arXiv
In colored graphs, node classes are often associated with either their neighbors class or with information not incorporated in the graph associated with each node. We here propose that node classes are also associated with topological features of the nodes. We use this association to improve Graph machine learning in general and specifically, Graph Convolutional Networks (GCN). First, we show that even in the absence of any external information on nodes, a good accuracy can be obtained on the prediction of the node class using either topological features, or using the neighbors class as an inp
Negative / Null Result ReportOpen accessMathematics
Nicolas Dupin · 2019 · arXiv
The discrete unit commitment problem with min-stop ramping constraints optimizes the daily production of thermal power plants (coal, gas, fuel units). For this problem, compact Integer Linear Programming (ILP) formulations have been designed to solve exactly small instances and heuristically real-size instances. This paper investigates whether Dantzig-Wolfe reformulation allows to improve the previous exact method and matheuristics. The extended ILP formulation is presented with the column generation algorithm to solve its linear relaxation. The experimental results show that the Dantzig-Wolfe
Negative / Null Result ReportOpen accessComputer Science
Yongsheng Lian · 2025 · arXiv
This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning evaluation: models are first fine-tuned on the specialized Countdown Game and then assessed on a suite of general-purpose reasoning benchmarks. Across all tasks, RL-trained models outperform their corresponding base models, although the degree of improvement differs by benchmark. Our parametric analysis offers practical guidance for RL-based LLM training. Increas
Negative / Null Result ReportOpen accessMathematics
Martina Zizza · 2024 · arXiv
In this paper we examine the discrete Shnirelman's inequality [Shnirelman A., 1985], which relates the $L^2$-distance of two discrete configurations of a fluid to the $L^1_tL^2_x$-norm of the vector field connecting them. Our proof is inspired by [Shnirelman A., 1985], where it was obtained $α=\frac{1}{64}$ in dimension $ν=2$, while here we get $α\geq\frac{2}{7}$. Moreover we prove that $α\geq\frac{1}{ν+1}$ for any dimension $ν\geq 3$. We point out that, even if this does not improve the bound in the continuous version, where it was proved that $α\geq\frac{2}{4+ν}$, with $ν\geq 3$, our bound i
Negative / Null Result ReportOpen accessComputer Science
Syed Assad, Mark Bradshaw, Ping Koy Lam · 2016 · arXiv
Amplification of quantum states is inevitably accompanied with the introduction of noise at the output. For protocols that are probabilistic with heralded success, noiseless linear amplification in theory may still possible. When the protocol is successful, it can lead to an output that is a noiselessly amplified copy of the input. When the protocol is unsuccessful, the output state is degraded and is usually discarded. Probabilistic protocols may improve the performance of some quantum information protocols, but not for metrology if the whole statistics is taken into consideration. We calcula
Negative / Null Result ReportOpen accessMathematics
Aihua Xia, Fuxi Zhang · 2011 · arXiv
Random events in space and time often exhibit a locally dependent structure. When the events are very rare and dependent structure is not too complicated, various studies in the literature have shown that Poisson and compound Poisson processes can provide adequate approximations. However, the accuracy of approximations does not improve or may even deteriorate when the mean number of events increases. In this paper, we investigate an alternative family of approximating point processes and establish Stein's method for their approximations. We prove two theorems to accommodate respectively the po
Negative / Null Result ReportOpen accessComputer Science
Seungwon Baek · 2006 · arXiv
We perform a combined analysis of $B \to ππ$ and $B \to πK$ decays with the current experimental data. Assuming SU(3) flavor symmetry and no new physics contributions to the topological amplitudes, we demonstrate that the conventional parametrization in the Standard Model (SM) does not describe the data very well, in contrast with a similar analysis based on the earlier data. It is also shown that the introduction of smaller amplitudes and reasonable SU(3) breaking parameters does not improve the fits much. Interpreting these puzzling behaviors in the SM as a new physics (NP) signal, we study
Negative / Null Result ReportOpen accessComputer Science
Tomoya Kurosawa, Hitomi Yanaka · 2023 · arXiv
Even in the era of massive language models, it has been suggested that character-level representations improve the performance of neural models. The state-of-the-art neural semantic parser for Discourse Representation Structures uses character-level representations, improving performance in the four languages (i.e., English, German, Dutch, and Italian) in the Parallel Meaning Bank dataset. However, how and why character-level information improves the parser's performance remains unclear. This study provides an in-depth analysis of performance changes by order of character sequences. In the exp
Negative / Null Result ReportOpen accessComputer Science
Tianjiao Ni, Minghao Qiao, Zhili Chen et al. · 2020 · arXiv
Differential privacy is widely used in data analysis. State-of-the-art $k$-means clustering algorithms with differential privacy typically add an equal amount of noise to centroids for each iterative computation. In this paper, we propose a novel differentially private $k$-means clustering algorithm, DP-KCCM, that significantly improves the utility of clustering by adding adaptive noise and merging clusters. Specifically, to obtain $k$ clusters with differential privacy, the algorithm first generates $n \times k$ initial centroids, adds adaptive noise for each iteration to get $n \times k$ clu
Negative / Null Result ReportOpen accessComputer Science
Chenming Tang, Xiuyu Wu, Yunfang Wu · 2023 · arXiv
Model ensemble has been in widespread use for Grammatical Error Correction (GEC), boosting model performance. We hypothesize that model ensemble based on the perplexity (PPL) computed by pre-trained language models (PLMs) should benefit the GEC system. To this end, we explore several ensemble strategies based on strong PLMs with four sophisticated single models. However, the performance does not improve but even gets worse after the PLM-based ensemble. This surprising result sets us doing a detailed analysis on the data and coming up with some insights on GEC. The human references of correct s
Negative / Null Result ReportOpen accessComputer Science
Guanzi Chen, Jiying Zhang, Xi Xiao et al. · 2022 · arXiv
In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships. However, current neural network approaches designed for hypergraphs are mostly shallow, thus limiting their ability to extract information from high-order neighbors. In this paper, we show both theoretically and empirically, that the performance of hypergraph neural networks does not improve as the number of layers increases, which is known as the over-smoothing problem. To avoid this issue, we develop a new deep hypergraph convolutional network called De
Negative / Null Result ReportOpen accessEngineering
Siqi Ye, Yong Long, Il Yong Chun · 2020 · arXiv
This paper applies the recent fast iterative neural network framework, Momentum-Net, using appropriate models to low-dose X-ray computed tomography (LDCT) image reconstruction. At each layer of the proposed Momentum-Net, the model-based image reconstruction module solves the majorized penalized weighted least-square problem, and the image refining module uses a four-layer convolutional neural network (CNN). Experimental results with the NIH AAPM-Mayo Clinic Low Dose CT Grand Challenge dataset show that the proposed Momentum-Net architecture significantly improves image reconstruction accuracy,
Negative / Null Result ReportOpen accessAgricultural and Biological Sciences
Roy Henha Eyono, Daniel Levenstein, Arna Ghosh et al. · 2026 · arXiv
Normalization is a critical operation in neural circuits. In the brain, there is evidence that normalization is implemented via inhibitory interneurons and allows neural populations to adjust to changes in the distribution of their inputs. In artificial neural networks (ANNs), normalization is used to improve learning in tasks that involve complex input distributions. However, it is unclear whether inhibition-mediated normalization in biological neural circuits also improves learning. Here, we explore this possibility using ANNs with separate excitatory and inhibitory populations trained on an
Negative / Null Result ReportOpen accessPhysics
Susanne Still, David A. Sivak, Anthony J. Bell et al. · 2012 · arXiv
A system responding to a stochastic driving signal can be interpreted as computing, by means of its dynamics, an implicit model of the environmental variables. The system's state retains information about past environmental fluctuations, and a fraction of this information is predictive of future ones. The remaining nonpredictive information reflects model complexity that does not improve predictive power, and thus represents the ineffectiveness of the model. We expose the fundamental equivalence between this model inefficiency and thermodynamic inefficiency, measured by dissipation. Our result
Negative / Null Result ReportOpen accessPhysics
Ilias Magoulas, Karthik Gururangan, Piotr Piecuch et al. · 2021 · arXiv
The short answer to the question in the title is 'no'. We identify classes of truncated configuration interaction (CI) wave functions for which the externally corrected coupled-cluster (ec-CC) approach using the three-body ($T_{3}$) and four-body ($T_{4}$) components of the cluster operator extracted from CI does not improve the results of the underlying CI calculations. Implications of our analysis, illustrated by numerical examples, for the ec-CC computations using truncated and selected CI methods are discussed. We also introduce a novel ec-CC approach using the $T_{3}$ and $T_{4}$ amplitud
Negative / Null Result ReportOpen accessComputer Science
Matthias Otth, Jonas Hübotter, Ido Hakimi et al. · 2025 · arXiv
Recent work has shown that language models can self-improve by maximizing their own confidence in their predictions, without relying on external verifiers or reward signals. In this work, we study the test-time scaling of language models for mathematical reasoning tasks, where the model's own confidence is used to select the most promising attempts. Surprisingly, we find that we can achieve significant performance gains by continuing only the most promising attempt, selected by the model's prefix-confidence. We systematically evaluate prefix-confidence scaling on five mathematical reasoning da
Negative / Null Result ReportOpen accessComputer Science
Yuto Nishida, Makoto Morishita, Hiroyuki Deguchi et al. · 2025 · arXiv
The $k$-nearest-neighbor language model ($k$NN-LM), one of the retrieval-augmented language models, improves the perplexity for given text by directly accessing a large datastore built from any text data during inference. A widely held hypothesis for the success of $k$NN-LM is that its explicit memory, i.e., the datastore, enhances predictions for long-tail phenomena. However, prior works have primarily shown its ability to retrieve long-tail contexts, leaving the model's performance remain underexplored in estimating the probabilities of long-tail target tokens during inference. In this paper
Negative / Null Result ReportOpen accessComputer Science
Hugo Meric, Jose Miguel Piquer · 2013 · arXiv
We study the design of a DVB-S2 system in order to maximise spectrum efficiency. This task is usually challenging due to channel variability. Modern satellite communications systems such as DVB-SH and DVB-S2 rely mainly on a time sharing strategy to optimise the spectrum efficiency. Recently, we showed that combining time sharing with hierarchical modulation can provide significant gains (in terms of spectrum efficiency) compared to the best time sharing strategy. However, our previous design does not improve the DVB-S2 performance when all the receivers experience low or large signal-to-noise
Negative / Null Result ReportOpen accessComputer Science
Taisuke Kobayashi · 2020 · arXiv
This paper proposes a new optimizer for deep learning, named d-AmsGrad. In the real-world data, noise and outliers cannot be excluded from dataset to be used for learning robot skills. This problem is especially striking for robots that learn by collecting data in real time, which cannot be sorted manually. Several noise-robust optimizers have therefore been developed to resolve this problem, and one of them, named AmsGrad, which is a variant of Adam optimizer, has a proof of its convergence. However, in practice, it does not improve learning performance in robotics scenarios. This reason is h
Negative / Null Result ReportOpen accessComputer Science
Domenic Rosati · 2023 · arXiv
Communication of scientific findings to the public is important for keeping non-experts informed of developments such as life-saving medical treatments. However, generating readable lay summaries from scientific documents is challenging, and currently, these summaries suffer from critical factual errors. One popular intervention for improving factuality is using additional external knowledge to provide factual grounding. However, it is unclear how these grounding sources should be retrieved, selected, or integrated, and how supplementary grounding documents might affect the readability or rele
Negative / Null Result ReportOpen accessComputer Science
Ushak Rahaman, Soebur Razzaque · 2021 · arXiv
The $ν_μ\to ν_e$ oscillation probability over short baseline ($\lesssim 1$~km) would be negligible in case the mixing matrix for three active neutrinos is unitary. However, in case of non-unitary mixing of three neutrinos, this probability would be non-negligible due to the so-called "zero distance" effect. Hence, the near detector of the accelerator experiments such as NO$ν$A can provide strong constraints on the parameters of the non-unitary mixing with very large statistics. By analyzing the NO$ν$A near detector data we find that the non-unitary mixing does not improve fits to the $ν_e$ or
Negative / Null Result ReportOpen accessAgricultural and Biological Sciences
Louis Jalouzot, Alexis Thual, Yair Lakretz et al. · 2025 · arXiv
We investigate optimal strategies for decoding perceived natural speech from fMRI data acquired from a limited number of participants. Leveraging Lebel et al. (2023)'s dataset of 8 participants, we first demonstrate the effectiveness of training deep neural networks to predict LLM-derived text representations from fMRI activity. Then, in this data regime, we observe that multi-subject training does not improve decoding accuracy compared to single-subject approach. Furthermore, training on similar or different stimuli across subjects has a negligible effect on decoding accuracy. Finally, we fin
Negative / Null Result ReportOpen accessComputer Science
Yulin Chen, He He, Chen Zhao · 2026 · arXiv
Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the learning dynamics of RLVR remain underexplored. In this paper, we reveal a counterintuitive phenomenon: among hard examples that the model initially struggles with, a substantial subset remains unlearnable even when correct rollouts are present. To understand the phenomenon, we first demonstrate that existing optimization and sampling techniques fail to resolve unlearnability. With cross-example gradient analysis, we show that unlearnable examples
Negative / Null Result ReportOpen accessComputer Science
Hyeong Kyu Choi, Xiaojin Zhu, Sharon Li · 2025 · arXiv
Multi-Agent Debate~(MAD) has emerged as a promising paradigm for improving the performance of large language models through collaborative reasoning. Despite recent advances, the key factors driving MAD's effectiveness remain unclear. In this work, we disentangle MAD into two key components--Majority Voting and inter-agent Debate--and assess their respective contributions. Through extensive experiments across seven NLP benchmarks, we find that Majority Voting alone accounts for most of the performance gains typically attributed to MAD. To explain this, we propose a theoretical framework that mo
Negative / Null Result ReportOpen accessComputer Science
Mitchell A. Gordon, Kevin Duh, Nicholas Andrews · 2020 · arXiv
Pre-trained universal feature extractors, such as BERT for natural language processing and VGG for computer vision, have become effective methods for improving deep learning models without requiring more labeled data. While effective, feature extractors like BERT may be prohibitively large for some deployment scenarios. We explore weight pruning for BERT and ask: how does compression during pre-training affect transfer learning? We find that pruning affects transfer learning in three broad regimes. Low levels of pruning (30-40%) do not affect pre-training loss or transfer to downstream tasks a
Negative / Null Result ReportOpen accessComputer Science
Tovly Deutsch, Masoud Jasbi, Stuart Shieber · 2020 · arXiv
Readability assessment aims to automatically classify text by the level appropriate for learning readers. Traditional approaches to this task utilize a variety of linguistically motivated features paired with simple machine learning models. More recent methods have improved performance by discarding these features and utilizing deep learning models. However, it is unknown whether augmenting deep learning models with linguistically motivated features would improve performance further. This paper combines these two approaches with the goal of improving overall model performance and addressing th
