# How can we constrain lagrange multipliers in svm dual by adding constraints in primal problem?

Consider svm-dual,i.e., \begin{align} &\text{maximize} \sum_{i=1}^n \alpha_i-\frac{1}{2\lambda} \sum_{i,j=1}^n \alpha_i \alpha_j y_i y_j K(x_i,x_j)\cr &\text{subject to, } 0\leq \alpha_i \leq 1 \end{align} where $K$ is the kernel matrix and $\lambda$ is the regualrization parameter.

I know that $\alpha_i$ is the share of $x_i$ in determining the hyperplane. My question is how can we constrain this share in primal problem? Put it another way, How can we constrain lagrange multipliers(i.e. dual variables) by adding constraints in primal problem?