We are investigating the distributed optimization problem,where a network of nodes works together to minimize a global objective that is a finite sum of their stored local functions.Since nodes exchange optimization p...We are investigating the distributed optimization problem,where a network of nodes works together to minimize a global objective that is a finite sum of their stored local functions.Since nodes exchange optimization parameters through the wireless network,large-scale training models can create communication bottlenecks,resulting in slower training times.To address this issue,CHOCO-SGD was proposed,which allows compressing information with arbitrary precision without reducing the convergence rate for strongly convex objective functions.Nevertheless,most convex functions are not strongly convex(such as logistic regression or Lasso),which raises the question of whether this algorithm can be applied to non-strongly convex functions.In this paper,we provide the first theoretical analysis of the convergence rate of CHOCO-SGD on non-strongly convex objectives.We derive a sufficient condition,which limits the fidelity of compression,to guarantee convergence.Moreover,our analysis demonstrates that within the fidelity threshold,this algorithm can significantly reduce transmission burden while maintaining the same convergence rate order as its no-compression equivalent.Numerical experiments further validate the theoretical findings by demonstrating that CHOCO-SGD improves communication efficiency and keeps the same convergence rate order simultaneously.And experiments also show that the algorithm fails to converge with low compression fidelity and in time-varying topologies.Overall,our study offers valuable insights into the potential applicability of CHOCO-SGD for non-strongly convex objectives.Additionally,we provide practical guidelines for researchers seeking to utilize this algorithm in real-world scenarios.展开更多
Objective To investigate the association between total homocysteine(tHcy)level in plasma and methylenetetrahydrofblate reductase(MTHFR)C677T and A1298C genetic polymorphisms in a Chinese Han nationality population wit...Objective To investigate the association between total homocysteine(tHcy)level in plasma and methylenetetrahydrofblate reductase(MTHFR)C677T and A1298C genetic polymorphisms in a Chinese Han nationality population with type 2 diabetes mellitus(T2DM)accompanied by dyslipidemia.Methods This case-control study enrolled T2DM patients with dyslipidemia and without dyslipidemia respectively.Sanger dideoxy-mediated chain-termination method was used to detect the gene polymorphisms of MTHFR C677T and A1298C.Plasma tHcy and lipid levels were measured as well.The genotype frequency and allele frequency between the dyslipidemia and non-dyslipidemia groups were compared by using Chi-square test.Plasma tHcy level ofT2DM patients who carried the different genotypes was compared by Student's t test.Results Finally,82 T2DM patients with dyslipidemia and 94 ones without dyslipidemia were included in this study.There was a significant correlation between tHcy level and MTHFR C677T gene polymorphism inT2DM patients(t=2.27,P=0.02).Moreover,the plasma tHcy level in the dyslipidemia patients who carried MTHFR 677TT genotype was significantly higher than that in those with CT+CC genotype(13.62+6.97 vs.10.95+3.62pmol/L,t=2.2O,P=0.03);while for patients without dyslipidemia,comparison of the tHcy level between those who carried the above two alleles showed no significantly difference(13.34±6.03 vs.12.04±5.09μmol/L,t=1.08,P=0.29).Conclusion MTHFR 677TT genotype might associate with higher tHcy level in T2DM patients with dyslipidemia.展开更多
基金supported in part by the Shanghai Natural Science Foundation under the Grant 22ZR1407000.
文摘We are investigating the distributed optimization problem,where a network of nodes works together to minimize a global objective that is a finite sum of their stored local functions.Since nodes exchange optimization parameters through the wireless network,large-scale training models can create communication bottlenecks,resulting in slower training times.To address this issue,CHOCO-SGD was proposed,which allows compressing information with arbitrary precision without reducing the convergence rate for strongly convex objective functions.Nevertheless,most convex functions are not strongly convex(such as logistic regression or Lasso),which raises the question of whether this algorithm can be applied to non-strongly convex functions.In this paper,we provide the first theoretical analysis of the convergence rate of CHOCO-SGD on non-strongly convex objectives.We derive a sufficient condition,which limits the fidelity of compression,to guarantee convergence.Moreover,our analysis demonstrates that within the fidelity threshold,this algorithm can significantly reduce transmission burden while maintaining the same convergence rate order as its no-compression equivalent.Numerical experiments further validate the theoretical findings by demonstrating that CHOCO-SGD improves communication efficiency and keeps the same convergence rate order simultaneously.And experiments also show that the algorithm fails to converge with low compression fidelity and in time-varying topologies.Overall,our study offers valuable insights into the potential applicability of CHOCO-SGD for non-strongly convex objectives.Additionally,we provide practical guidelines for researchers seeking to utilize this algorithm in real-world scenarios.
基金the National Key Development Plan for Precision Medicine Research(2017YFC0910004)Jinan Science Project(201602171),and Jinan Science and Technology Plan Project(201503009).
文摘Objective To investigate the association between total homocysteine(tHcy)level in plasma and methylenetetrahydrofblate reductase(MTHFR)C677T and A1298C genetic polymorphisms in a Chinese Han nationality population with type 2 diabetes mellitus(T2DM)accompanied by dyslipidemia.Methods This case-control study enrolled T2DM patients with dyslipidemia and without dyslipidemia respectively.Sanger dideoxy-mediated chain-termination method was used to detect the gene polymorphisms of MTHFR C677T and A1298C.Plasma tHcy and lipid levels were measured as well.The genotype frequency and allele frequency between the dyslipidemia and non-dyslipidemia groups were compared by using Chi-square test.Plasma tHcy level ofT2DM patients who carried the different genotypes was compared by Student's t test.Results Finally,82 T2DM patients with dyslipidemia and 94 ones without dyslipidemia were included in this study.There was a significant correlation between tHcy level and MTHFR C677T gene polymorphism inT2DM patients(t=2.27,P=0.02).Moreover,the plasma tHcy level in the dyslipidemia patients who carried MTHFR 677TT genotype was significantly higher than that in those with CT+CC genotype(13.62+6.97 vs.10.95+3.62pmol/L,t=2.2O,P=0.03);while for patients without dyslipidemia,comparison of the tHcy level between those who carried the above two alleles showed no significantly difference(13.34±6.03 vs.12.04±5.09μmol/L,t=1.08,P=0.29).Conclusion MTHFR 677TT genotype might associate with higher tHcy level in T2DM patients with dyslipidemia.
